Key papers

• AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation (2026)
  Kien T. Pham et al.
  8.42
• Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering (2026)
  Yanjie Zhang et al.
  6.25
• Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric Absorption (2026)
  Xiaomeng Fu et al.
  5.89
• Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs (2026)
  Yoonhyung Park et al.
  5.49
• Contrastive On-Policy Distillation (2026)
  Jiacheng Ruan et al.
  5.49
• Mixture of Probes: Learning from Privileged Modalities in Multimodal LLMs Through Probing (2026)
  Dominick Reilly et al.
  5.01
• A Coreset Selection Framework with Ensemble Aggregation for Image Classification (2026)
  Pedro Rocha Dantas et al.
  5.01
• SceneBind: Binding What and Where Across Vision, Audio and Language (2026)
  Mingfei Chen et al.
  5.01
• Webly Supervised Multi-Label Recognition: Evaluation Benchmark and Dual-Branch Multi-Label Contrastive Learning (2026)
  Zhihua Xu et al.
  5.01
• Scale Up Strategically: Learning Compositional Generalization via Bias-Aware Evaluation and Data Collection for Robotic Manipulation (2026)
  Yu Qi et al.
  5.01
• Direct Preference Optimization for Chatbot Fine-Tuning: An Empirical Study (2026)
  Dezhi Yu et al.
  4.95
• From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models (2026)
  Haoxiang Sun et al.
  4.95
• NaviCache: Test-Time Self-Calibration Caching for Video Generation (2026)
  Zheqi Lv et al.
  4.95
• Vertigo Vertigo: Reconstructing a Cinematic Ideal through its Predictive AI Double (2026)
  Adam Cole et al.
  4.39
• CV-DCLR: Causal-Visual Dynamic Label Refinement for Robust Zero-Shot Learning (2026)
  Can Wang et al.
  4.39
• Robustness Meets Uncertainty: Evidential Adversarial Training for Robust Selective Classification (2026)
  Nicolas Sournac et al.
  4.39
• A Step Towards Robust Unsupervised Domain Adaptation via Fine-Tuning and Reinforcement Learning (2026)
  Sushant Dagaji Desale et al.
  4.39
• SiamJEPA: On the Role of Siamese Student Encoders in JEPA (2026)
  Makoto Yamada
  4.39
• Binary Iterative Method for Non-targeted Adversarial Attack (2026)
  Naman Goyal et al.
  4.39
• SAD-LoRA: Spectral Alignment for Low-Rank Knowledge Distillation (2026)
  Omer Tariq et al.
  4.39
• Hierarchical Scaffolding Enables Human-Like Cognitive Selectivity under Data Scarcity (2026)
  Juhyoung Park et al.
  4.39
• Learning Probabilistic Prompt for Continual Learning (2026)
  Hyekang Park et al.
  4.39
• Virtual Category-Guided Continual Generalized Category Discovery (2026)
  Jiahui Xiong et al.
  4.39
• Beyond Modality Fusion: Deep Ensembles for Multimodal Classification (2026)
  Ilya Burenko et al.
  4.39
• RSLoRA: Training-free Rank Allocation for LoRA via Representational Sensitivity Probing (2026)
  Jiaqi Liu et al.
  4.39
• Time Imprint: Learning Time-Aware Representations in Multi-Modal Knowledge Graphs (2026)
  Pengyu Zhang et al.
  4.39
• A Strong Balanced-Softmax Classifier-Retraining Baseline for Long-Tailed Recognition (2026)
  Juan Terven et al.
  4.39
• Reliability-Aware Ensemble Classification Under Class Imbalance: A Calibration Study on Liquid-Based Cervical Cytology (2026)
  Nisreen Albzour et al.
  4.39
• Bridging the Catalog-to-Real Gap: Scalable Product Recognition via Multi-Stage Contrastive Learning (2026)
  Anyi Zhang et al.
  4.39
• SISA-Rec: A Semantically Integrated Sequential Recommender with Contrastive Alignment (2026)
  Soohan Abbasi et al.
  4.39
• Single-Teacher View Augmentation: Enhancing Knowledge Distillation with Student-Guided Perturbations (2026)
  Xuyi Yu et al.
  4.39
• Similarity-Guided Curriculum Fine-Tuning of LLMs for Neural Architecture Synthesis (2026)
  Anujaya Vijayakumar et al.
  4.39
• Continual Learning with Elastic Regularization and Synthetic Replay for Federated MLLM Fine-Tuning (2026)
  Jing Liu et al.
  4.39
• Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training? (2026)
  Nusrat Munia et al.
  4.39
• DP-BOA: Dirichlet-Process Birth-or-Assign for On-the-Fly Category Discovery (2026)
  Peiyan Gu et al.
  4.39
• AspectCLIP: Optimizing CLIP Representation Space via Aspect-Guided Consistency Regularization (2026)
  Yiyang Yao et al.
  4.39
• Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case Study (2026)
  Zhan Chen et al.
  4.39
• CT-Merging: Consensus Directions and Task-Level Scaling for LoRA Adapter Merging (2026)
  Keumseo Ryum et al.
  4.39
• A Deep Reinforcement Learning (DRL)-Based Transformer Method for Solving the Open Shop Scheduling Problem (2026)
  Faezeh Ardali et al.
  4.33
• TwinBI: An Agentic Digital Twin for Efficient Augmented Interactions with Business Intelligence Dashboards (2026)
  Jisoo Jang Wen-Syan Li
  4.33
• Numbers Already Carry Their Own Embeddings (2026)
  Suhyun Bae et al.
  4.33
• Thinking Outside the [Chat]Box: Bridging Computer Science and Industrial Design for Cognitive-Inclusive Generative AI (2026)
  Virginia Francisco et al.
  4.33
• Design Methodology and Performance Trade-offs Management for Distributed and Compound AI Systems (2026)
  Milos Gravara et al.
  4.33
• MoECa: Aligning Feature Reuse with Expert Decomposition in Diffusion Transformers (2026)
  Maoliang Li et al.
  4.33
• SUP-MCRL: Subject-aware Unified Pseudo-feature Coded Multimodal Contrastive Representation Learning for EEG Visual Decoding (2026)
  Shengyu Gong et al.
  4.33
• The Token Is a Group Element: On Lie-Algebra Attention over Matrix Lie Groups (2026)
  Przemyslaw Musialski
  4.33
• MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning (2026)
  Wenhao Wang et al.
  4.33
• Systematic Exploration of 4-Expert Heterogeneous Mixture-of-Experts via Automated Pipeline Search (2026)
  Yashkumar R Lukhi et al.
  4.33
• Efficient Cross-Scale Invertible Hiding Network with Spatial-Frequency Collaboration and Non-Invertible Mechanism (2026)
  Junxue Yang et al.
  4.33
• OracleAnalyser: Analysing Implicit Semantics of Oracle Bone Scripts through MLLMs with Post-training (2026)
  Zijia Song et al.
  4.33
• Neural Subspace Reallocation: Continual Learning as Retrieval-Based Subspace Memory Management (2026)
  Byeong Hoon Yoon
  4.33
• On the Vulnerability of Parameter-Level Defenses to Model Merging (2026)
  Kuangpu Guo et al.
  4.33
• CLIMB: Centroid-Based Hierarchical Memory for Online Continual Self-Supervised Learning (2026)
  Julien Lefebvre et al.
  4.33
• MAPE: Defending Against Transferable Adversarial Attacks Using Multi-Source Adversarial Perturbations Elimination (2026)
  Xinlei Liu et al.
  4.33
• Revising RVL-CDIP: Quantifying Errors and Test-Train Overlap (2026)
  Stefan Larson et al.
  4.33
• REDI: Corpus Aware Patch Ranking for DINOv3 Token Reduction (2026)
  Chanjong Im et al.
  4.33
• MIMIC: A Generative Multimodal Foundation Model For Biomolecules (2026)
  Siavash Golkar, Jake Kovalic, Irina Espejo Morales, et al.
  4.20
• Fine-tuning DeepSeek-OCR-2 for Molecular Structure Recognition (2026)
  Haocheng Tang and Xingyu Dang and Junmei Wang
  4.09
• MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale (2026)
  Bin Wang et al.
  4.09
• Adarubric: Task-adaptive Rubrics For LLM Agent Evaluation (2026)
  Liang Ding
  3.85