{"total":59,"rows":[{"id":"2507.16869","title":"Controllable Video Generation: A Survey","created":"2025-07-22","cited_by_count":98,"area":null},{"id":"2510.17845","title":"MAT-Agent: Adaptive Multi-Agent Training Optimization","created":"2025-10-10","cited_by_count":35,"area":null},{"id":"2509.02785","title":"DrDiff: Dynamic Routing Diffusion with Hierarchical Attention for Breaking the Efficiency-Quality Trade-off","created":"2025-09-02","cited_by_count":34,"area":null},{"id":"2509.04876","title":"OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration","created":"2025-09-05","cited_by_count":30,"area":"agents"},{"id":"2602.17659","title":"When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs","created":"2026-02-19","cited_by_count":30,"area":"vla"},{"id":"2602.05551","title":"FastVMT: Eliminating Redundancy in Video Motion Transfer","created":"2026-02-05","cited_by_count":23,"area":null},{"id":"2510.10035","title":"Failure-Driven Workflow Refinement","created":"2025-10-11","cited_by_count":20,"area":null},{"id":"2512.08240","title":"Hybrid Token Compression for Vision-Language Models","created":"2025-12-09","cited_by_count":20,"area":"mllm"},{"id":"2510.11978","title":"Learning Dynamics of VLM Finetuning","created":"2025-10-13","cited_by_count":17,"area":"alignment"},{"id":"2510.22391","title":"Top-Down Semantic Refinement for Image Captioning","created":"2025-10-25","cited_by_count":16,"area":"mllm"},{"id":"2510.22710","title":"RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliability","created":"2025-10-26","cited_by_count":14,"area":"lr"},{"id":"2509.09703","title":"CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation Backdoor","created":"2025-09-05","cited_by_count":12,"area":"safety"},{"id":"2511.13211","title":"3DAlign-DAER: Dynamic Attention Policy and Efficient Retrieval Strategy for Fine-grained 3D-Text Alignment at Scale","created":"2025-11-17","cited_by_count":12,"area":null},{"id":"2603.22883","title":"Group Editing: Edit Multiple Images in One Go","created":"2026-03-24","cited_by_count":11,"area":null},{"id":"2512.18477","title":"STORM: Search-Guided Generative World Models for Robotic Manipulation","created":"2025-12-20","cited_by_count":7,"area":"wm"},{"id":"2509.25178","title":"GHOST: Hallucination-Inducing Image Generation for Multimodal LLMs","created":"2025-09-29","cited_by_count":4,"area":"mllm"},{"id":"2512.22536","title":"CoAgent: Collaborative Planning and Consistency Agent for Coherent Video Generation","created":"2025-12-27","cited_by_count":4,"area":null},{"id":"2512.07500","title":"MultiMotion: Multi Subject Video Motion Transfer via Video Diffusion Transformer","created":"2025-12-08","cited_by_count":3,"area":"diffusion"},{"id":"2601.04699","title":"SeqWalker: Sequential-Horizon Vision-and-Language Navigation with Hierarchical Planning","created":"2026-01-08","cited_by_count":3,"area":null},{"id":"2508.20828","title":"GDLLM: A Global Distance-aware Modeling Approach Based on Large Language Models for Event Temporal Relation Extraction","created":"2025-08-28","cited_by_count":2,"area":null},{"id":"2511.19923","title":"Distilling Counterfactual Reasoning from Language to Vision: Causal Graph Guided Post-Training for Video Understanding","created":"2025-11-25","cited_by_count":2,"area":"lr"},{"id":"2512.18489","title":"Large Language Models as Discounted Bayesian Filters","created":"2025-12-20","cited_by_count":2,"area":null},{"id":"2512.18496","title":"Adaptive-VoCo: Complexity-Aware Visual Token Compression for Vision-Language Models","created":"2025-12-20","cited_by_count":2,"area":"mllm"},{"id":"2603.11110","title":"ResWM: Residual-Action World Model for Visual RL","created":"2026-03-11","cited_by_count":2,"area":"wm"},{"id":"2606.23206","title":"CFPO: Counterfactual Policy Optimization for Multimodal Reasoning","created":"2026-06-22","cited_by_count":2,"area":"lr"},{"id":"2510.22467","title":"Backward-Friendly Optimization: Training Large Language Models with Approximate Gradients under Memory Constraints","created":"2025-10-26","cited_by_count":1,"area":null},{"id":"2510.22477","title":"Agent-GSPO: Communication-Efficient Multi-Agent Systems via Group Sequence Policy Optimization","created":"2025-10-26","cited_by_count":1,"area":null},{"id":"2512.18605","title":"Reflective Confidence: Correcting Reasoning Flaws via Online Self-Correction","created":"2025-12-21","cited_by_count":1,"area":"lr"},{"id":"2512.20604","title":"MoE-DiffuSeq: Enhancing Long-Document Diffusion Models with Sparse Attention and Mixture of Experts","created":"2025-12-23","cited_by_count":1,"area":"diffusion"},{"id":"2601.08189","title":"ForgetMark: Stealthy Fingerprint Embedding via Targeted Unlearning in Language Models","created":"2026-01-13","cited_by_count":1,"area":"safety"},{"id":"2602.07689","title":"Process-of-Thought Reasoning for Videos","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2603.25357","title":"InstanceAnimator: Multi-Instance Sketch Video Colorization","created":"2026-03-26","cited_by_count":1,"area":"diffusion"},{"id":"2608.28138","title":"Token-Budget Distillation: Transferring Full-Token Semantics to Compressed Video Vision-Language Models","created":"2026-08-28","cited_by_count":1,"area":"mllm"},{"id":"2510.09887","title":"Overconfident and Blind to Details: Fixing Prompt Insensitivity with Abductive Preference Learning","created":"2025-10-10","cited_by_count":0,"area":"alignment"},{"id":"2510.22473","title":"DynaPose4D: High-Quality 4D Dynamic Content Generation via Pose Alignment Loss","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2510.22859","title":"Guardian: Decoupling Exploration from Safety in Reinforcement Learning","created":"2025-10-26","cited_by_count":0,"area":"deeprl"},{"id":"2512.00812","title":"Causal Invariance and Counterfactual Learning Driven Cooperative Game for Multi-Label Classification","created":"2025-11-30","cited_by_count":0,"area":null},{"id":"2512.18504","title":"GTMA: Dynamic Representation Optimization for OOD Vision-Language Models","created":"2025-12-20","cited_by_count":0,"area":"mllm"},{"id":"2512.18614","title":"PTTA: A Pure Text-to-Animation Framework for High-Quality Creation","created":"2025-12-21","cited_by_count":0,"area":null},{"id":"2512.20531","title":"SirenPose: Dynamic Scene Reconstruction via Geometric Supervision","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2512.20724","title":"SA-DiffuSeq: Addressing Computational and Scalability Challenges in Long-Document Generation with Sparse Attention","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2512.20920","title":"RevFFN: Memory-Efficient Full-Parameter Fine-Tuning of Mixture-of-Experts LLMs with Reversible Blocks","created":"2025-12-24","cited_by_count":0,"area":"moe"},{"id":"2512.22294","title":"A Three-Level Alignment Framework for Large-Scale 3D Retrieval and Controlled 4D Generation","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2512.22295","title":"Learning Dynamic Scene Reconstruction with Sinusoidal Geometric Priors","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2512.22378","title":"Towards Efficient Post-Training via Fourier-Driven Adapter Architectures","created":"2025-12-26","cited_by_count":0,"area":null},{"id":"2512.22545","title":"Self-Rewarded Multimodal Coherent Reasoning Across Diverse Visual Domains","created":"2025-12-27","cited_by_count":0,"area":"lr"},{"id":"2601.09726","title":"Forgetting as a Feature: Cognitive Alignment of Large Language Models","created":"2025-12-28","cited_by_count":0,"area":"alignment"},{"id":"2602.00292","title":"LogicGaze: Benchmarking Causal Consistency in Visual Narratives via Counterfactual Verification","created":"2026-01-30","cited_by_count":0,"area":"lr"},{"id":"2602.00340","title":"Bridging the Semantic Chasm: Synergistic Conceptual Anchoring for Generalized Few-Shot and Zero-Shot OOD Perception","created":"2026-01-30","cited_by_count":0,"area":"mllm"},{"id":"2602.15330","title":"A Scalable Curiosity-Driven Game-Theoretic Framework for Long-Tail Multi-Label Learning in Data Mining","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2602.23191","title":"Uni-Animator: Towards Unified Visual Colorization","created":"2026-02-26","cited_by_count":0,"area":"diffusion"},{"id":"2603.07784","title":"ProgAgent:A Continual RL Agent with Progress-Aware Rewards","created":"2026-03-08","cited_by_count":0,"area":"alignment"},{"id":"2607.13931","title":"SIVA-RL: Sensitivity-Invariance Visual Alignment for Multimodal Reinforcement Learning","created":"2026-07-15","cited_by_count":0,"area":"lr"},{"id":"2609.03429","title":"When Do Frozen VLMs Respond to Image-Free Object-Token Edits? An Answer-Key-Free Protocol and What It Reveals","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.17953","title":"EDCT-Bench: Uncovering Faithfulness Gaps in VLMs via Explanation-Driven Counterfactual Testing","created":"2026-09-16","cited_by_count":0,"area":"mllm"},{"id":"2609.24172","title":"LegendBench: A Diagnostic Benchmark for Legend Understanding with Counterfactual Interventions","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.37638","title":"Targeted Visual Counterfactual Explanations for Contrastive Vision-Language Model","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"id":"2610.12530","title":"CacheScope: Exact-Compute Allocation for Training-Free Diffusion Acceleration","created":"2026-10-08","cited_by_count":0,"area":"diffusion"},{"id":"2610.13910","title":"When VLMs Destroy What They Know: Spatial Representations Fall Below Lexical Priors","created":"2026-10-09","cited_by_count":0,"area":"mllm"}],"next_cursor":null}