π― What it does: An unsupervised semantic segmentation framework COMUS is proposed, which utilizes self-supervised features and unsupervised saliency detection for object discovery, and enhances multi-object segmentation through iterative self-training.
π― What it does: A two-dimensional visualization method based on contrastive learning, t-SimCNE, is proposed for unsupervised mapping of image data to a two-dimensional space.
Phillip Swazinna (Siemens and Technical University of Munich), Thomas Runkler (Siemens and Technical University of Munich)
CodeReinforcement LearningTabularBenchmark
π― What it does: Designed and implemented LION, an offline reinforcement learning algorithm that allows real-time control of the proximity between the policy and the original policy by adjusting the hyperparameter Ξ» after deployment, enabling user interactive adjustment.
Lisa Dunlap (University of California Berkeley), Anna Rohrbach (University of California Berkeley)
CodeDomain AdaptationTransformerVision Language ModelContrastive LearningImageMultimodality
π― What it does: This paper proposes a language description-based domain expansion method called LADS, which utilizes the multimodal embedding space of CLIP to map training domain image features to unseen domains through language guidance, thereby improving cross-domain performance without using target domain images.
π― What it does: Using Conditional Selective Inference to provide testable p-values for significant regions generated by deep learning, thereby quantifying the reliability of significant regions.
π― What it does: This paper proposes the Value Memory Graph (VMG), a world model that aggregates offline RL data into a directed graph after mapping it to a metric space. It employs value iteration and Dijkstra multi-step search control for agents on this graph, achieving efficient learning for sparse rewards and long-horizon tasks.
Variational Information Pursuit for Interpretable Predictions
Aditya Chattopadhyay (Johns Hopkins University), Rene Vidal (University of Pennsylvania)
CodeClassificationExplainability and InterpretabilityComputational EfficiencyConvolutional Neural NetworkReinforcement LearningImageTextBiomedical Data
π― What it does: A variational information tracking (V-IP) method is proposed, which directly learns the query selection strategy and classifier using deep networks, achieving interpretable predictions without relying on generative models.
π― What it does: A Variational Latent Branch Model (VLBM) is designed and implemented to learn MDP transitions from limited coverage offline trajectories and perform offline policy evaluation.
Verifying the Union of Manifolds Hypothesis for Image Data
Bradley CA Brown, Gabriel Loaiza-Ganem (Layer 6 AI)
CodeClassificationGenerationAuto EncoderImage
π― What it does: This paper experimentally verifies that image data better fits the 'multi-manifold union' hypothesis, proving that the support set of the data is discrete and that different subsets have different intrinsic dimensions.
π― What it does: This paper proposes a single-frame weakly supervised video scene graph generation task and automatically generates localized scene graphs for each frame in the video through a Pseudo Label Assignment framework (PLA), enabling the training of fully supervised models without the need for complete video-level annotations.
π― What it does: This paper proposes a point cloud-based view synthesis method called Sculpted Neural Points (SNP), which utilizes initial point clouds generated by multi-view stereo (MVS) and achieves high-quality, fast view synthesis through global sculpting (point pruning and point augmentation) and differentiable rendering.
π― What it does: A text-supervised semantic segmentation is performed by constructing a multi-view consistency learning framework (ViewCo) to enhance the consistency of segmentation across different view images and cross-modal semantic alignment.
π― What it does: This paper proposes a visual reward and representation learning framework based on Value Implicit Pre-training (VIP), which can self-supervisedly learn a network from massive offline human videos that can generate dense rewards and serve as general visual features.
π― What it does: An offline reinforcement learning algorithm named VIPER is proposed, which achieves conservatism (pessimism) by adding random noise to the rewards and using the minimum of multiple models, thereby achieving theoretically provable effectiveness without explicitly constructing confidence intervals.
π― What it does: A pre-trained, task-agnostic adapter named ViT-Adapter is proposed, which transforms a standard Vision Transformer into a model suitable for dense prediction tasks (object detection, instance segmentation, semantic segmentation) through convolutional priors and multi-scale feature reconstruction.
Minghuan Liu (Shanghai Jiaotong University), Zhongwen Xu (Sea AI Lab)
CodeExplainability and InterpretabilityRobotic IntelligenceConvolutional Neural NetworkReinforcement LearningImage
π― What it does: Proposes the PatchAIL framework, which uses a patch-based discriminator to generate dense rewards for visual imitation learning, balancing efficiency and interpretability.
π― What it does: A Deep Nearest Center (DNC) network is proposed, using a non-parametric nearest center decision instead of the traditional softmax classifier;
Weizhi Wang (University of California), Furu Wei (Microsoft Research)
CodeRetrievalTransformerLarge Language ModelVision Language ModelImageTextMultimodalityRetrieval-Augmented Generation
π― What it does: Introducing retrieval-based visual completion during the pre-training phase of the language model, dynamically retrieving and integrating corresponding image information for each text token, thereby achieving visually enhanced autoregressive language modeling.
VoGE: A Differentiable Volume Renderer using Gaussian Ellipsoids for Analysis-by-Synthesis
Angtian Wang (Johns Hopkins University), Alan Yuille (Johns Hopkins University)
CodePose EstimationImage
π― What it does: Using a differentiable voxel renderer VoGE, the geometry of objects is represented by 3D Gaussian ellipsoids to achieve volume rendering;
π― What it does: This paper proposes a multi-view point cloud representation, where each 3D point is described by a set of features from multiple views, and designs VointNet to learn feature aggregation in this space.
π― What it does: A voxel-based neural surface reconstruction method called Voxurf is proposed, capable of completing high-quality surface reconstruction in just a few minutes.
π― What it does: A weight space rotation (WaRP) reparameterization method is proposed for class-incremental few-shot learning, which can effectively learn new categories while preserving old knowledge.
π― What it does: This paper proposes a framework based on Wasserstein Autoencoders (WAE-MDP) for distilling deep reinforcement learning (DRL) policies into discrete verifiable subspace models, and ensures the formal verification of the original policy by approximating parallel execution that guarantees the formalized Bisimulation property.
π― What it does: A deep learning-based audio sequence tokenizer called wav2tok is proposed, which can learn semantic discrete tokens from similar audio pairs for efficient retrieval.
Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic
Zijun Wu (University of Alberta), Lili Mou (University of Alberta)
CodeExplainability and InterpretabilityTransformerLarge Language ModelText
π― What it does: We propose a weakly supervised interpretable phrase reasoning model EPR to accomplish the natural language inference task; the model first detects phrases, aligns corresponding phrases, predicts phrase-level logical relationships, and then derives sentence-level labels through neural fuzzy logic.
Weakly Supervised Knowledge Transfer with Probabilistic Logical Reasoning for Object Detection
Martijn Oldenhof (KU Leuven), Edward De Brouwer (KU Leuven)
CodeObject DetectionTransformerImage
π― What it does: Proposes the ProbKT framework, which utilizes probabilistic logic reasoning to achieve weakly supervised knowledge transfer for object detection.
π― What it does: A weakly supervised human-object interaction (HOI) detection framework is proposed, utilizing the CLIP pre-trained model to construct a dual-layer knowledge base, injecting prior knowledge at both the image level and alignment level, and suppressing erroneous human-object associations through a self-learning correlation classifier, ultimately achieving end-to-end weakly supervised HOI detection.
Ruixuan Yan (Rensselaer Polytechnic Institute), Anak Agung Julius
CodeGenerationOptimizationExplainability and InterpretabilityTabularTime SeriesElectronic Health Records
π― What it does: A neural-symbolic framework called Clock Logic Neural Network (CLNN) is proposed, which explains the generation mechanism of multivariate event streams and predicts event occurrences by learning weighted clock logic formulas (wCL).
π― What it does: A systematic evaluation of 523 ImageNet pre-trained models was conducted regarding their performance in uncertainty estimation (selective prediction, calibration, etc.), and influencing factors were explored.
π― What it does: A long sequence modeling framework SGConv based on global convolution is proposed, and it is integrated as a general module into Transformer, ConvNet, and visual models.
When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning
Jianxiong Li (Institute for Artificial Intelligence Industry Research), Ya-Qin Zhang (Institute for Artificial Intelligence Industry Research)
CodeReinforcement LearningTabularBenchmark
π― What it does: The DOGE algorithm is proposed, which combines the geometric information of the dataset with the approximation error characteristics of the deep Q function in offline reinforcement learning. It utilizes a state-conditioned distance function as a policy constraint to achieve reasonable utilization of the OOB region.
Alihan HΓΌyΓΌk (University of Cambridge), Mihaela van der Schaar (University of Cambridge)
CodeOptimizationReinforcement LearningTabularBiomedical Data
π― What it does: This paper proposes a new Optimal Commitment Problem (OCP) aimed at helping decision-makers determine when to break commitments to avoid future costs, and potentially shift to other commitments or cease commitments altogether.
WikiWhy: Answering and Explaining Cause-and-Effect Questions
Matthew Ho (University of California), William Yang Wang (University of California)
CodeGenerationRetrievalExplainability and InterpretabilityTransformerLarge Language ModelPrompt EngineeringTextRetrieval-Augmented GenerationChain-of-Thought
π― What it does: A WIKIWHY dataset was constructed, collecting 9,406 Wikipedia-based 'why' question-answer and explanation triples;
Win: Weight-Decay-Integrated Nesterov Acceleration for Adaptive Gradient Algorithms
Pan Zhou (Sea AI Lab), Shuicheng YAN
CodeOptimizationTransformerImageText
π― What it does: A general acceleration framework named WeightβDecayβIntegrated Nesterov Acceleration (WIN) is proposed to enhance the convergence speed and final performance of adaptive gradient optimizers such as AdamW, Adam, LAMB, and SGD.
Write and Paint: Generative Vision-Language Models are Unified Modal Learners
Shizhe Diao (Hong Kong University of Science and Technology), Jiawei Wang (Shanghai Jiao Tong University)
CodeGenerationData SynthesisTransformerVision Language ModelImageTextMultimodality
π― What it does: This paper proposes a unified prefix multimodal pre-training framework, constructing a general visual-language foundation model DAVINCI that can simultaneously learn 'writing' (image β text) and 'painting' (text β image).
π― What it does: A zero-shot image restoration framework DDNM and its improved version DDNM+ are proposed, utilizing a pre-trained denoising diffusion model and null space decomposition, capable of solving any linear inverse problem (such as super-resolution, deblurring, colorization, compressed sensing, inpainting, etc.) without training any networks, and supporting noise recovery.
ZiCo: Zero-shot NAS via inverse Coefficient of Variation on Gradients
Guihong Li (University of Texas at Austin), Radu Marculescu (University of Texas at Austin)
CodeOptimizationNeural Architecture SearchImage
π― What it does: A new zero-shot NAS proxy, ZiCo, is proposed, which predicts network performance using the inverse coefficient of gradient mean and variance to directly search for the optimal network.