🎯 What it does: Proposed the Restoration Score Distillation (RSD) framework, which learns high-fidelity generative models from only corrupted observations through a two-stage training process (pre-training with a corruption-aware diffusion model, followed by distilling it into a first-order generator).
Score-based Greedy Search for Structure Identification of Partially Observed Causal Models
Xinshuai Dong (Carnegie Mellon University), Kun Zhang (Carnegie Mellon University)
CodeScore-based ModelTabular
🎯 What it does: Propose a greedy search algorithm called LGES based on maximum likelihood scores for identifying structures in partially observed linear causal models with latent variables, and prove its asymptotic consistency under the Generalized N Factor Model condition.
SCoT: Teaching 3D-LLMs to Think Spatially with Million-scale CoT Annotations
Jinpeng Li (LIESMARS, Wuhan University), Bisheng Yang (LIESMARS, Wuhan University)
CodeExplainability and InterpretabilityData-Centric LearningVision Language ModelMultimodalityPoint CloudChain-of-Thought
🎯 What it does: Proposed and constructed a three-tier spatial Chain-of-Thought (SCoT) dataset with a scale of 1.1M, aimed at training and evaluating the spatial reasoning capabilities of 3D large language models in three categories of tasks: perception, analysis, and planning.
SCRAPL: Scattering Transform with Random Paths for Machine Learning
Christopher Mitcheltree (Queen Mary University of London), Mathieu Lagrange (Ecole Centrale Nantes)
CodeRestorationGenerationData SynthesisAudio
🎯 What it does: Developed a random path scattering transform (Scattering Transform) approximation algorithm called SCRAPL, which utilizes random sampling and path-specific optimization methods to achieve a differentiable, computationally efficient scattering transform loss for unsupervised training in audio inverse problems.
SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning
Shicheng Liu (Stanford University), Xin Luna Dong
CodeData-Centric LearningAI Code AssistantLarge Language ModelReinforcement LearningText
🎯 What it does: Developed a reinforcement learning-based framework called SCRIBES to generate generalizable extraction scripts for efficiently extracting semi-structured data at web scale.
Search Self-Play: Pushing the Frontier of Agent Capability without Supervision
Hongliang Lu (Alibaba), guanjunjiang
CodeTransformerLarge Language ModelReinforcement LearningAgentic AITextRetrieval-Augmented Generation
🎯 What it does: Designed and implemented an unsupervised deep search agent self-learning method called Search Self-Play (SSP), enabling LLMs to alternate between the roles of questioner and solver within the same model, and verifying the correctness of questions through Retrieval-Augmented Generation (RAG) to achieve co-evolution of agent capabilities.
Searching for Privacy Risks in LLM Agents via Simulation
Yanzhe Zhang (Georgia Tech), Diyi Yang (Stanford University)
CodeSafty and PrivacyAdversarial AttackTransformerLarge Language ModelAgentic AIPrompt EngineeringText
🎯 What it does: This paper systematically identifies and quantifies privacy leakage risks in multi-round dialogues between LLM agents through a framework based on simulation and alternating search, while iteratively generating robust defense strategies.
SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPC
Jinglong Luo (Pengcheng Laboratory), Zenglin Xu (Fudan University)
CodeDomain AdaptationSafty and PrivacyTransformerLarge Language ModelPrompt EngineeringTextFinance Related
🎯 What it does: In this paper, the authors propose SecP-Tuning, a privacy-preserving prompt tuning framework based on secure multiparty computation (MPC), specifically designed for efficiently adapting large language models (LLMs) to sensitive domains such as healthcare and finance;
SEED: Towards More Accurate Semantic Evaluation for Visual Brain Decoding
Juhyeon Park (Seoul National University), Taesup Moon (Seoul National University)
CodeExplainability and InterpretabilityRepresentation LearningConvolutional Neural NetworkTransformerLarge Language ModelImageTextBiomedical DataBenchmark
🎯 What it does: Proposed the SEED (Semantic Evaluation for Visual Brain Decoding) metric to better evaluate the semantic reconstruction quality of visual brain decoding models
SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From
Yao Tong (National University of Singapore), Tianyang Hu (Chinese University of Hong Kong)
CodeTransformerLarge Language ModelTextBenchmark
🎯 What it does: Proposes a persistent fingerprint called SeedPrints, generated based on the model's random initialization seed, to trace the origin and inheritance of LLMs throughout the entire training process.
Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models
Jiaying Wu (National University Of Singapore), Bryan Hooi (National University Of Singapore)
CodeData SynthesisAnomaly DetectionTransformerLarge Language ModelPrompt EngineeringVision Language ModelMultimodalityBenchmark
🎯 What it does: This paper investigates the deception intent of creators in multi-modal news and proposes the DECEPTIONDECODED benchmark for generating image-text news with explicit deceptive intent.
Seeing Through the Brain: New Insights from Decoding Visual Stimuli with fMRI
Zheng Huang (Dartmouth College), Yujun Yan (UNC Charlotte)
CodeGenerationData SynthesisTransformerLarge Language ModelPrompt EngineeringDiffusion modelTextBiomedical DataMagnetic Resonance Imaging
🎯 What it does: Propose the PRISM framework, which maps fMRI signals to a structured text space and then generates visual stimuli images using text-guided diffusion models.
Seeing Through Words: Controlling Visual Retrieval Quality with Language Models
Jianglin Lu (Adobe Research), Yun Fu (Northeastern University)
CodeRetrievalLarge Language ModelSupervised Fine-TuningPrompt EngineeringVision Language ModelImageTextMultimodality
🎯 What it does: This work proposes a quality-controllable retrieval framework, QCQC, which enhances the quality and controllability of text-to-image retrieval by appending descriptions matching specified quality (relevance and aesthetics) to short queries using a large language model.
Seeing What’s Wrong: A Trajectory-Guided Approach to Caption Error Detection
Gabriel Afriat (Massachusetts Institute of Technology), Rahul Mazumder (IBM Research)
CodeAnomaly DetectionExplainability and InterpretabilityLarge Language ModelVision Language ModelContrastive LearningMultimodality
🎯 What it does: Propose the TRACED framework, which detects subtitle errors by generating and analyzing image-caption trajectories, while providing explainability and error correction guidance.
Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
Lin Long (Zhejiang University), Wei Li (Zhejiang University)
CodeRetrievalGraph Neural NetworkLarge Language ModelReinforcement LearningVideoTextMultimodalityBenchmarkRetrieval-Augmented GenerationAudio
🎯 What it does: Proposed M3-Agent—a multimodal agent with long-term memory capable of real-time perception, constructing event and semantic memories, and completing tasks through multi-round reasoning and memory retrieval.
Segment-Level Attribution for Selective Learning of Long Reasoning Traces
Siyuan Wang (University of Southern California), Xiang Ren (University of Southern California)
CodeExplainability and InterpretabilityKnowledge DistillationTransformerSupervised Fine-TuningTextChain-of-Thought
🎯 What it does: This paper proposes a paragraph-level importance assessment method based on integrated gradients, and applies it to implement selective fine-tuning (Selective SFT) on long-chain reasoning (CoT), thereby improving reasoning accuracy and compressing output length.
🎯 What it does: Proposed the SR2 framework, treating reasoning tasks as causal selection mechanisms, utilizing a three-step iterative process consisting of reflective representation learning, dependency self-refinement, and periodic alignment to enhance reasoning capabilities.
CodeLarge Language ModelReinforcement LearningMixture of ExpertsTextBenchmark
🎯 What it does: This paper proposes the MENTOR framework, which achieves high-quality exploration in RLVR by providing expert guidance to LLMs at critical decision points;
Self-Aligned Reward: Towards Effective and Efficient Reasoners
Peixuan Han (University of Illinois Urbana Champaign), Luyang Kong (Amazon Web Services)
CodeComputational EfficiencyLarge Language ModelReinforcement LearningText
🎯 What it does: Investigated an internal reward mechanism called Self-Aligned Reward (SAR) for reinforcement learning training of large language models, enabling them to more precisely and effectively evaluate answer quality and improve reasoning efficiency in reasoning tasks.
Self-Consistency Improves the Trustworthiness of Self-Interpretable GNNs
Wenxin Tai (University of Electronic Science and Technology of China), Fan Zhou (University of Electronic Science and Technology of China)
CodeExplainability and InterpretabilityGraph Neural NetworkSupervised Fine-TuningGraphBenchmark
🎯 What it does: Proposes incorporating a self-consistency (SC) fine-tuning strategy into self-explaining graph neural networks (SI-GNN) to directly optimize the credibility and consistency of model explanations during training.
Yuhui Wang (Stony Brook University), Ting Wang (Stony Brook University)
CodeSafty and PrivacyAdversarial AttackTransformerLarge Language ModelText
🎯 What it does: Under adversarial fine-tuning attacks, the proposed SEAM method transforms LLMs into self-destructing models, retaining normal task capabilities while experiencing performance collapse when subjected to harmful fine-tuning;
🎯 What it does: Propose a self-guided low-light object detection framework that employs a detachable auxiliary pipeline (including self-supervised enhancement, denoising, and Fourier fusion) during training, but adds no modules or parameters during inference.
Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement Learning
Seungyul Han (Ulsan National Institute of Science and Technology), Yisak Park (Ulsan National Institute of Science and Technology)
CodeMeta LearningReinforcement LearningBenchmark
🎯 What it does: Proposed the self-improving skill learning framework (SISL), achieving robust skill primitive meta reinforcement learning in long-horizon tasks with noisy offline demonstrations.
Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training
Zheng Xin Yong, Stephen Bach
CodeSafty and PrivacyExplainability and InterpretabilityTransformerLarge Language ModelPrompt EngineeringTextRetrieval-Augmented GenerationChain-of-Thought
🎯 What it does: Discovered and systematically studied the phenomenon of self-escape in reasoning language models during chain-of-thought reasoning, where models bypass their own safety defenses through internal reasoning without external attacks;
Self-Speculative Decoding Accelerates Lossless Inference in Any-Order and Any-Subset Autoregressive Models
Gabe Guo (Stanford University), Stefano Ermon (Stanford University)
CodeGenerationComputational EfficiencyTransformerLarge Language ModelSupervised Fine-TuningText
🎯 What it does: Proposed Any Subset Autoregressive Model (AS-ARM) and Arbitrary Subset Speculative Decoding (ASSD), achieving parallel efficient filling generation in any order.
🎯 What it does: Studied the one-to-many mapping problem in natural alignment data, proposing the AdaSSL method which introduces latent variables to capture conditional uncertainty, thereby improving the positive sample similarity modeling in self-supervised learning.
SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?
Michael Kirchhof (Apple), Sinead Williamson (Apple)
CodeExplainability and InterpretabilityTransformerLarge Language ModelSupervised Fine-TuningReinforcement LearningPrompt EngineeringTextBenchmarkRetrieval-Augmented Generation
🎯 What it does: This paper proposes the SelfReflect metric to evaluate whether a single text faithfully summarizes the internal answer distribution of a large language model (LLM) under a given query, and experimentally examines whether modern LLMs can naturally generate self-reflective uncertainty expressions; further, the metric is open-sourced along with benchmark evaluation code.
SelvaBox: A high‑resolution dataset for tropical tree crown detection
Hugo Baudchon (Mila - Quebec AI Institute), Etienne Laliberté (Université de Montréal)
CodeObject DetectionConvolutional Neural NetworkTransformerImageBenchmarkAgriculture Related
🎯 What it does: This paper constructs the largest tropical tree crown detection dataset, SELVABOX, and achieves state-of-the-art detection performance in both tropical and non-tropical scenarios through multi-scale, transformation-agnostic training and a Transformer-based detection model.
SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks
Mingqian Feng (University of Rochester), Jianfeng Gao (Microsoft Research)
CodeAdversarial AttackLarge Language ModelReinforcement LearningText
🎯 What it does: Propose the SEMA framework, which trains a multi-round hacking model without strategy or external data using reinforcement learning with prefilling self-tuning and intent drift-aware reward mechanisms;
Semantic Uncertainty Quantification of Hallucinations in LLMs: A Quantum Tensor Network Based Method
pragatheeswaran vipulanandan, Dilip Sarkar (University of Miami)
CodeAnomaly DetectionExplainability and InterpretabilityTransformerLarge Language ModelText
🎯 What it does: Propose an unsupervised method for hallucination detection and answer selection by quantifying the probability uncertainty of LLM-generated sequences, combining quantum tensor networks (QTN) with semantic Rényi entropy.
Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks
Chunyang Jiang (Hong Kong University of Science and Technology), Yike Guo (Hong Kong University of Science and Technology)
CodeComputational EfficiencyRepresentation LearningLarge Language ModelContrastive LearningText
🎯 What it does: Proposes a self-assessment-free semantic voting framework that uses sentence embeddings to perform soft voting on LLM-generated answers, generating pseudo-labels for self-improvement
Semantic-aware Wasserstein Policy Regularization for Large Language Model Alignment
Byeonghu Na (KAIST), Il-chul Moon
CodeReinforcement Learning from Human FeedbackLarge Language ModelReinforcement LearningText
🎯 What it does: Propose a policy regularization framework (WPR) based on entropy-regularized Wasserstein distance for aligning large language models in reinforcement learning from human feedback (RLHF);
Semantic-Enhanced Time-Series Forecasting via Large Language Models
Hao Liu (University of Science and Technology Beijing), Xiaobin Zhu (University of Science and Technology Beijing)
CodeRecurrent Neural NetworkTransformerLarge Language ModelAuto EncoderTime Series
🎯 What it does: Proposed a new time series forecasting framework called SE-LLM, which leverages the pre-trained knowledge of large language models (LLMs) and further enhances the understanding and prediction of time series through the TSCC module and Time-Adapter.
Semi-Supervised Preference Optimization with Limited Feedback
Seonggyun Lee (Yonsei University), Kyungwoo Song (Yonsei University)
CodeOptimizationData-Centric LearningReinforcement Learning from Human FeedbackLarge Language ModelSupervised Fine-TuningReinforcement LearningContrastive LearningTextBenchmark
🎯 What it does: Propose a semi-supervised preference optimization framework called SSPO, which jointly trains using a small amount of labeled preference comparisons and a large amount of unlabeled SFT data.
SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillation
Xingtong Ge (Hong Kong University of Science and Technology), Jun Zhang (Hong Kong University of Science and Technology)
CodeGenerationKnowledge DistillationVision Language ModelFlow-based ModelImageTextMultimodality
🎯 What it does: This paper extends Distribution Matching Distillation (DMD) to large-scale streaming text-image models, proposing SenseFlow, which includes Implicit Distribution Alignment (IDA), Intra-Segment Guidance (ISG), and a discriminator based on visual foundation models, achieving four-step high-quality generation.
Yisi Luo (Xi'an Jiaotong University), Deyu Meng (Xi'an Jiaotong University)
CodeOptimizationComputational EfficiencyRepresentation LearningImageMeshPhysics Related
🎯 What it does: This paper provides a theoretical analysis of separable neural networks (SepNN), proving their universal approximation capability, deriving the convergence properties of their neural tangent kernel (NTK) under conditions of infinite width/rank and fixed rank, and proposing an efficient separable preconditioned gradient descent (SepPGD) algorithm to alleviate spectrum bias.
SERE: Similarity-based Expert Re-routing for Efficient Batch Decoding in MoE Models
Juntong Wu (Taobao & Tmall Group of Alibaba), Li Yuan (Peking University)
CodeComputational EfficiencyMixture of ExpertsText
🎯 What it does: Proposed a dynamic rerouting method called SERE based on expert similarity to accelerate batch decoding in MoE models, significantly reducing the number of activated experts while maintaining model performance.
SeRI: Gradient-Free Sensitive Region Identification in Decision-Based Black-Box Attacks
Feiyang Wang (Beijing University of Posts and Telecommunications), Hangwei Qian (Victoria University of Wellington)
CodeAdversarial AttackImage
🎯 What it does: In the hard-label black-box attack scenario where only the model's top-1 predicted label is observable and the query budget is limited, a decision-benchmark method called SeRI is designed to continuously evaluate and refine the sensitivity of each pixel in the image. It is integrated as a plugin into existing attackers to improve attack efficiency.
SERQ: Saliency-Aware Low-Rank Error Reconstruction for LLM Quantization
Yeonsik Park (Kyung Hee University), Seungkyu Choi (Yonsei University)
CodeOptimizationComputational EfficiencyKnowledge DistillationTransformerLarge Language ModelText
🎯 What it does: Proposes SERQ, a significance-aware error reconstruction method using a single low-rank matrix, enabling full low-precision inference for LLMs under W4A4/W4A8 precision;
SERUM: Simple, Efficient, Robust, and Unifying Marking for Diffusion-based Image Generation
Jan Kociszewski (CISPA Helmholtz Center for Information Security), Adam Dziedzic (CISPA Helmholtz Center for Information Security)
CodeGenerationDiffusion modelImage
🎯 What it does: Propose a method that injects a unique watermark noise into the initial noise of a diffusion model and trains a lightweight detector to mark generated images
🎯 What it does: Propose the SFBD-OMNI framework, which restores the original data distribution through alternating minimization under limited clean samples and a large number of corrupted samples.
CodeAI Code AssistantLarge Language ModelAgentic AIPrompt EngineeringTextBenchmark
🎯 What it does: Proposed and implemented a shared program state abstraction, enabling LLMs to directly read and write variables, objects, and control flow within programs, simplifying natural language programming.
🎯 What it does: This paper proposes the SHARP method, which uses a single image to regress a high-resolution 3D Gaussian representation through a neural network in less than one second, enabling real-time realistic rendering of nearby views.
CodeOptimizationSafty and PrivacyAdversarial AttackConvolutional Neural NetworkTransformerImage
🎯 What it does: Investigated the behavior and effectiveness of Sharpness-Aware Minimization (SAM) in machine unlearning tasks, provided theoretical analysis and experimental verification, and proposed a new hierarchical unlearning algorithm called Sharp MinMax based on these findings.
Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference Optimization
Haocheng Luo (Monash University), Trung Le (Monash University)
CodeOptimizationReinforcement Learning from Human FeedbackTransformerLarge Language ModelText
🎯 What it does: This paper investigates the convergence and alignment issues in Direct Preference Optimization (DPO), elucidates the essence of the squeezing effect, and proposes an efficient variant called logits-SAM that applies SAM in the logits space, significantly enhancing the performance and robustness of DPO and its variants.
SHE-LoRA: Selective Homomorphic Encryption for Federated Tuning with Heterogeneous LoRA
Jianmin Liu (Xi'an Jiaotong University), Chao Shen (Xi'an Jiaotong University)
CodeFederated LearningSafty and PrivacyLarge Language ModelSupervised Fine-TuningText
🎯 What it does: Proposed the SHE-LoRA framework, integrating Selective Homomorphic Encryption (SHE) with Low-Rank Adaptation (LoRA), to achieve efficient privacy-preserving cross-device federated fine-tuning of large language models (LLMs).
Stefano Fiorini (Istituto Italiano di Tecnologia), Stefano Coniglio
CodeClassificationGraph Neural NetworkGraph
🎯 What it does: This paper proposes Directed Cellular Sheaf and the corresponding Directed Sheaf Laplacian L˜F, and builds the Directed Sheaf Neural Network (DSNN), achieving a graph neural network that explicitly captures edge direction information in directed graphs;
🎯 What it does: The paper proposes Cumulative Self-Consistency Loss (CSL), improving diffusion/flow matching generative models with a control-theoretic perspective, enhancing few-step generation quality, and linking it to reinforcement learning.
Should We Still Pretrain Encoders with Masked Language Modeling?
Hippolyte Gisserot-Boukhlef (Artefact Research Center), Pierre Colombo (Cohere)
CodeClassificationRetrievalComputational EfficiencyRepresentation LearningData-Centric LearningTransformerLarge Language ModelSupervised Fine-TuningText
🎯 What it does: Compared the effectiveness of using masked language models (MLM) and causal language models (CLM) in encoder pre-training, and proposed two-stage (CLM+MLM) and continuous pre-training (CPT) strategies
Si-GT: Fast Interconnect Signal Integrity Analysis for Integrated Circuit Design via Graph Transformers
Yuting Hu (University at Buffalo), Jinjun Xiong (University at Buffalo)
CodeComputational EfficiencyGraph Neural NetworkTransformerMeshGraphPhysics Related
🎯 What it does: Proposed a Si-GT model based on graph transformer for fast and accurate prediction of crosstalk delay and noise in integrated circuit (IC) interconnects;
Lihe Yang (University of Hong Kong), Hengshuang Zhao (Shanghai AI Laboratory)
CodeComputational EfficiencyKnowledge DistillationRepresentation LearningTransformerVision Language ModelContrastive LearningMultimodalityBenchmark
🎯 What it does: Through 'fine-to-coarse' supervision, fine-grained features from high-resolution images are migrated to standard-resolution visual encoders, enhancing the visual perception capabilities of multimodal LLMs.
SIGMark: Scalable In-Generation Watermark with Blind Extraction for Video Diffusion
Xinjie zhu, Weifeng Zhang (Lenovo Research)
CodeGenerationDiffusion modelOptical FlowVideo
🎯 What it does: Proposed a scalable blind watermark generation framework called SIGMark for modern video diffusion models, which can achieve information embedding and extraction without affecting video quality;
Daniil Medyakov (Basic Research of Artificial Intelligence Laboratory), Aleksandr Beznosikov (Basic Research of Artificial Intelligence Laboratory)
CodeOptimizationComputational EfficiencyTransformerLarge Language ModelSupervised Fine-TuningImageText
🎯 What it does: Designed and implemented a SIGN-SGD optimizer (ALIAS) without manual learning rate tuning, along with its memory-efficient and momentum-enabled variants, and validated its effectiveness in training large-scale language and vision models.
Xilin Wei (Fudan University), Dahua Lin (Shanghai AI Laboratory)
CodeExplainability and InterpretabilityComputational EfficiencyTransformerLarge Language ModelSupervised Fine-TuningTextBenchmarkChain-of-Thought
🎯 What it does: Propose SIM-CoT, a training module that introduces step-level supervision into implicit chain-of-thought, utilizing an auxiliary decoder to align each implicit token with corresponding explicit reasoning steps, thereby enhancing the stability and diversity of implicit CoT.
🎯 What it does: Proposed a dual-system Vision-Language-Action (VLA) framework called Sim2Real-VLA, which can achieve zero-shot transfer to real-world robotic manipulation tasks after training solely on synthetic data.
🎯 What it does: Proposes the SiMO framework, enabling multimodal collaborative perception to maintain normal operation even when any unimodal sensor fails.
SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs
Yuling Gu (Allen Institute for AI), Yejin Choi (Stanford University)
CodeLarge Language ModelTextBenchmarkChain-of-Thought
🎯 What it does: This paper proposes and constructs the SimpleToM dataset to evaluate the capabilities of large language models in explicit theory of mind (ToM) reasoning and implicit behavior prediction/judgment under diverse everyday scenarios.
🎯 What it does: Proposed a reinforcement learning framework called SimpleVLA-RL, which utilizes sparse rewards based solely on task completion to perform online training of Vision-Language-Action models, thereby enhancing long-term action planning and generality in data-scarce scenarios;
SimuHome: A Temporal- and Environment-Aware Benchmark for Smart Home LLM Agents
Gyuhyeon Seo (Seoul National University), Yohan Jo (Seoul National University)
CodeLarge Language ModelWorld ModelTextBenchmark
🎯 What it does: Developed SimuHome—a real-time accelerated smart home simulator based on the Matter protocol and a multi-task evaluation benchmark with 600 sentences;
🎯 What it does: This paper proposes a knowledge distillation framework based on zero-space guided energy redistribution (SiNGER), addressing the high norm artifact problem in visual Transformers. It applies low-rank perturbations only in the zero space of the next layer on teacher features using a lightweight LoRA adapter to eliminate artifacts while preserving useful information.
SK2Decompile: LLM-based Two-Phase Binary Decompilation from Skeleton to Skin
Hanzhuo Tan (Southern University of Science and Technology), Yuqun Zhang (Southern University of Science and Technology)
CodeAI Code AssistantTransformerLarge Language ModelReinforcement LearningText
🎯 What it does: Propose a two-stage framework based on large language models for binary decompilation, first generating intermediate representation (IR) via a structural recovery model, then producing readable source code through an identifier naming model;
SketchingReality: From Freehand Scene Sketches to Photorealistic Images
Ahmed Bourouis (University of Surrey), Yulia Gryaditskaya (University of Surrey)
CodeGenerationConvolutional Neural NetworkVision Language ModelDiffusion modelImageTextMultimodality
🎯 What it does: Propose a model based on stable diffusion that can generate high-quality photorealistic images from freehand scene sketches and text prompts.
SketchThinker-R1: Towards Efficient Sketch-Style Reasoning in Large Multimodal Models
Ruiyang Zhang (University of Macau), Zhedong Zheng (University of Macau)
CodeComputational EfficiencyLarge Language ModelSupervised Fine-TuningReinforcement LearningVision Language ModelMultimodalityChain-of-Thought
🎯 What it does: Proposed the SketchThinker-R1 framework, which employs a three-phase training process (Sketch-Mode Cold Start, SketchJudge Reward Model, Sketch-Thinking RL) to enable large-scale multimodal models to generate concise sketch-style reasoning, significantly reducing token consumption.
🎯 What it does: This paper proves that under the Mutual Information Skill Learning (MISL) framework, Contrastive Successor Features (CSF) learned features can reconstruct the environment's true state under linear transformations, completing identifiability analysis;
🎯 What it does: Restructure the model's self-generated reasoning trajectories into silver supervision data incorporating verification and retry behaviors. First, preheat the model using supervised fine-tuning (SFT), then further enhance reasoning capabilities through reinforcement learning (RL).
🎯 What it does: Released SkyEvents, a large-scale, event-enhanced UAV dataset integrating synchronized RGB, event, LiDAR, and precise 6-DoF poses for city-scale 3D reconstruction.
🎯 What it does: Propose an SLA scheme that categorizes the attention of diffusion Transformers into three types: key, edge, and ignorable. FlashAttention is used to compute key blocks, linear attention processes edge blocks, and ignorable blocks are skipped, significantly reducing O(N²) computation.
Y. Isabel Liu (Princeton University), Tom Silver (Princeton University)
CodeRobotic IntelligenceReinforcement Learning
🎯 What it does: In existing task and motion planning (TAMP) frameworks, reinforcement learning is introduced to automatically discover new low-level options (shortcuts), using these shortcuts to compress paths in the abstract planning graph, thereby significantly improving the execution efficiency of long-horizon sparse-reward tasks.
🎯 What it does: Proposed a slice Wasserstein (DSW) metric based on Banach space to replace the computationally expensive Wasserstein over Wasserstein (WoW) distance.
SliderQuant: Accurate Post-Training Quantization for LLMs
Shigeng Wang (Intel Labs China), Anbang Yao (Intel Labs China)
CodeComputational EfficiencyTransformerLarge Language ModelText
🎯 What it does: This paper proposes the SliderQuant framework, which achieves post-training quantization for high-precision LLMs by reducing quantization errors through adaptive sliding windows for layer-wise optimization.
SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks
Seungwon Jeong (Dongguk University), Woojin Lee (Dongguk University)
CodeAdversarial AttackTransformerLarge Language ModelPrompt EngineeringText
🎯 What it does: Addressing jailbreaking attacks on LLMs, the study investigates the importance of insertion positions (slots) and proposes the SlotGCG method
SMAN-Bench: A Cross-System Benchmark for Mobile Agents under Single- and Multi-path, Ambiguous, and Noisy Tasks
Weikai Xu (Nanyang Technological University), Bo An (Tsinghua University)
CodeVision Language ModelGraphBenchmarkRetrieval-Augmented Generation
🎯 What it does: Proposed the SMAN-Bench cross-system mobile agent benchmark, covering single-path, multi-path, ambiguous, and noisy tasks, and implemented offline multi-path evaluation along with noise/ambiguous subsets.
SmellNet: A Dataset for Sensor-Based Smell Recognition and Mixture Prediction
Dewei Feng (MIT), Paul Pu Liang (MIT)
CodeClassificationRecognitionTransformerContrastive LearningTime Series
🎯 What it does: Proposed the SMELLNET dataset and the SCENTFORMER model, aiming to achieve real-time machine olfaction based on low-cost metal oxide sensors;
🎯 What it does: A single-channel uncertainty estimation method based on self-supervised next activation prediction is studied, which can provide reliable error detection and model confidence with only one forward inference and no labels on TinyML devices.
🎯 What it does: This paper constructs SocialJax, a JAX-based sequential social dilemma environment and algorithm suite, providing a complete training pipeline, benchmark evaluation metrics, and multiple baseline algorithm implementations.
🎯 What it does: Propose a Soft Equivariant Regularization (SER) that separates equivariance and invariance across different network layers to enhance the performance of self-supervised learning in Vision Transformers (ViT).
Saeed Hedayatian (University of Southern California), Stefanos Nikolaidis (University of Southern California)
CodeOptimizationImageBenchmark
🎯 What it does: Propose the Soft Quality Diversity (SOFT QD) framework and differentiable algorithm SQUAD to address discretization issues and high-dimensional challenges in traditional Quality Diversity (QD) methods.
Michael Hersche (IBM Research), Abbas Rahimi (ETH Zurich)
CodeGenerationAI Code AssistantTransformerLarge Language ModelSupervised Fine-TuningDiffusion modelText
🎯 What it does: Propose the Soft-Masking method, which during the decoding process of Mask Diffusion Language Models (MDLM), combines the [MASK] token with the top-k word vectors predicted in the previous step through a convex combination, thereby preserving predictive information and providing continuous feedback.
SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization
Huashan Sun (Alibaba Group), Fei Huang (Alibaba Group)
CodeReinforcement Learning from Human FeedbackLarge Language ModelReinforcement LearningTextChain-of-Thought
🎯 What it does: This paper proposes a framework called SoLoPO, which decomposes long-text preference optimization into short-text preference optimization and short-to-long reward alignment, thereby improving training efficiency and model generalization.
SONA: Learning Conditional, Unconditional, and Matching-Aware Discriminator
Yuhta Takida (Sony AI), Yuki Mitsufuji (Sony AI)
CodeGenerationGenerative Adversarial NetworkImage
🎯 What it does: Proposed a new discriminator design called SONA aimed at addressing the balance between realism and conditional alignment in conditional generation.
🎯 What it does: Proposed the SongEcho framework for generating new singing and accompaniment under given original singer melody and text prompts, achieving full-song cover generation.
Gijs Joppe Moens (Netherlands Cancer Institute), Eduardo H P Pooch
CodeClassificationSegmentationConvolutional Neural NetworkImageBiomedical Data
🎯 What it does: Proposed the SONIC module, a convolutional alternative based on continuous spectral parameterization, achieving global receptive field and resolution-invariant convolution operations through direction-aware low-rank spectral filters;
SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations
Wentao Guo (Princeton University), Tri Dao (Princeton University)
CodeOptimizationComputational EfficiencyMixture of ExpertsText
🎯 What it does: This paper proposes SonicMoE, a comprehensive system for fine-grained and sparse MoE training, including memory-efficient forward/backward algorithms, GPU kernels with overlapping IO and arithmetic operations, and block-size-based Token Rounding routing.
SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward
Kaixuan Fan (MMLab, Chinese University of Hong Kong), Xiangyu Yue (MMLab, Chinese University of Hong Kong)
CodeReinforcement Learning from Human FeedbackTransformerLarge Language ModelReinforcement LearningVision Language ModelMultimodality
🎯 What it does: The Trust-GRPO reinforcement learning framework, which combines global thinking rewards and rule-based rewards, was used to train the multimodal large language model SophiaVL-R1 to enhance its reasoning capabilities.
🎯 What it does: Achieve real-time acceleration for vision-language-action (VLA) models through joint model scheduling and spatial semantic dual perception token pruning.
SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence
Ziyang Gong (Shanghai Jiao Tong University), Rongrong Ji (Xiamen University)
CodeLarge Language ModelVision Language ModelMultimodalityPoint CloudBenchmark
🎯 What it does: This paper introduces SpaCE-10, a benchmark dataset for evaluating the spatial reasoning capabilities of multimodal large language models.
SpaCE-Eval: A Benchmark for Real-World Multi-Modal Reasoning
Xuyou Yang (Singapore University of Technology and Design), Immanuel Koh (Singapore University of Technology and Design)
CodeLarge Language ModelVision Language ModelImageTextMultimodalityBenchmark
🎯 What it does: Proposes the SpaCE-Eval benchmark to evaluate the capabilities of multimodal large language models in real-world spatial reasoning, common sense knowledge, and environmental interaction.
Yizhao Gao (The University of Hong Kong), Mao Yang (Microsoft Research)
CodeComputational EfficiencyKnowledge DistillationTransformerLarge Language ModelText
🎯 What it does: For long-sequence decoding in inference models, this paper proposes SeerAttention-R, a sparse attention framework that achieves dynamic block-level sparse decoding through a lightweight gating module while keeping the original model parameters unchanged.
SparseD: Sparse Attention for Diffusion Language Models
Zeqing Wang (National University of Singapore), Xinchao Wang (National University of Singapore)
CodeGenerationComputational EfficiencyTransformerLarge Language ModelDiffusion modelTextMultimodalityBenchmark
🎯 What it does: Propose the SparseD sparse attention scheme, specifically designed for diffusion language models (DLM), aiming to significantly improve inference speed while maintaining original performance, particularly suitable for long-context scenarios.
SparseEval: Efficient Evaluation of Large Language Models by Sparse Optimization
Taolin Zhang (Shenzhen University), Jindong Wang (Tsinghua University)
CodeOptimizationComputational EfficiencyTransformerLarge Language ModelTextBenchmark
🎯 What it does: Propose an efficient large language model evaluation framework called SparseEval based on sparse optimization, which can approximate the complete evaluation results by selecting a small number of representative samples (anchors) and learning weights for them.
Spatial CAPTCHA: Generatively Benchmarking Spatial Reasoning for Human-Machine Differentiation
Arina Kharlamova (Mohamed bin Zayed University of Artificial Intelligence), Xue Liu (City University of Hong Kong)
CodeGenerationData SynthesisImageBenchmark
🎯 What it does: Proposed a spatial reasoning-based CAPTCHA generation framework (Spatial CAPTCHA) and its corresponding benchmark dataset (Spatial-CAPTCHA-Bench), achieving programmable, adjustable difficulty CAPTCHA generation.
SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
Hongxing Li (Zhejiang University), Yueting Zhuang (Zhejiang University)
CodeTransformerSupervised Fine-TuningReinforcement LearningVision Language ModelImageVideoTextMultimodalityChain-of-Thought
🎯 What it does: Proposed the SpatialLadder-26k multimodal dataset and a three-stage progressive training framework, systematically building the spatial reasoning capabilities of vision-language models from object localization → spatial understanding → spatial reasoning.
SpatialViz-Bench: A Cognitively-Grounded Benchmark for Diagnosing Spatial Visualization in MLLMs
Siting Wang (Chinese Academy of Sciences), Jun Wang (University College London)
CodeData SynthesisLarge Language ModelVision Language ModelMultimodalityBenchmarkChain-of-Thought
🎯 What it does: Proposes SpatialViz-Bench, a multi-modal benchmark based on cognitive science for evaluating the spatial visualization capabilities of large language models.
SpecBranch: Speculative Decoding via Hybrid Drafting and Rollback-Aware Branch Parallelism
Yuhao Shen (Zhejiang University), Cong Wang (Zhejiang University)
CodeComputational EfficiencyTransformerLarge Language ModelTextBenchmark
🎯 What it does: Propose SpecBranch, a framework that achieves parallel speculative decoding through branch resampling and hybrid rollback-aware draft length prediction, to accelerate large language model inference.
SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start
Kun Chen (University of Chinese Academy of Sciences), Lin Ma (Meituan)
CodeKnowledge DistillationRepresentation LearningReinforcement Learning from Human FeedbackTransformerLarge Language ModelSupervised Fine-TuningReinforcement LearningVision Language ModelMultimodality
🎯 What it does: Proposes a three-stage self-distillation preference cold start framework (SPECS), which significantly improves model reasoning performance in multi-modal reasoning tasks by generating preference data through self-distillation, using DPO for pre-alignment, and then applying GRPO reinforcement learning.
SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery
Lorenzo Caselli (University of Florence), Andrew D. Bagdanov (University of Florence)
CodeClassificationKnowledge DistillationRepresentation LearningVision Language ModelContrastive LearningMultimodality
🎯 What it does: Propose the SpectralGCD method, which utilizes CLIP's image-concept similarity as a unified cross-modal representation, trains a parameterized classifier within GCD, and enhances performance through spectral filtering and forward-backward knowledge distillation.
SpectraLLM: Uncovering the Ability of LLMs for Molecule Structure Elucidation from Multi-Spectra
Yunyue Su (New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences), Zhaoxiang Zhang (New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences)
CodeComputational EfficiencyRepresentation LearningDrug DiscoveryTransformerLarge Language ModelSupervised Fine-TuningPrompt EngineeringTextMultimodalityBiomedical Data
🎯 What it does: Using large language models to infer molecular structures from various spectra (IR, Raman, UV-Vis, NMR, MS) and uniformly process both single-modal and multi-modal inputs;