Key papers

• SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video Understanding (2026)
  Ahmed Y. Radwan et al.
  1.94
• Temporal Gains, Spatial Costs: Revisiting Video Fine-Tuning in Multimodal Large Language Models (2026)
  Linghao Zhang et al.
  1.94
• HiMu: Hierarchical Multimodal Frame Selection for Long Video Question Answering (2026)
  Dan Ben-Ami et al.
  1.94
• What Really Controls Temporal Reasoning in Large Language Models: Tokenisation or Representation of Time? (2026)
  Gagan Bhatia et al.
  1.94
• VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding (2026)
  Ruoliu Yang et al.
  1.94
• VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification (2026)
  Jiahao Meng et al.
  1.94
• OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video (2026)
  Junfu Pu et al.
  1.94
• Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents (2026)
  Seyed Moein Abtahi et al.
  1.94
• Nexus : An Agentic Framework for Time Series Forecasting (2026)
  Sarkar Snigdha Sarathi Das et al.
  1.94
• ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment (2026)
  Qiuyu Tian et al.
  1.94
• HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers (2026)
  Guozhen Zhang et al.
  1.94
• Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning (2026)
  Hohin Kwan et al.
  1.94
• Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics (2026)
  Maciej Chrabąszcz et al.
  1.89
• Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines (2026)
  Alimurtaza Mustafa Merchant et al.
  1.89
• Small Vision-Language Models are Smart Compressors for Long Video Understanding (2026)
  Junjie Fei et al.
  1.83
• Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory (2026)
  Weixian Waylon Li et al.
  1.83
• When AI Navigates the Fog of War (2026)
  Ming Li et al.
  1.78
• Region-Adaptive Sampling for Diffusion Transformers (2025)
  Ziming Liu et al.
  1.28
• VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning (2025)
  Ye Liu et al.
  1.28
• Video-R1: Reinforcing Video Reasoning in MLLMs (2025)
  Kaituo Feng et al.
  1.28
• VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning (2025)
  Xinhao Li et al.
  1.28
• Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Images (2025)
  Boyang Deng et al.
  1.28
• Self-alignment of Large Video Language Models with Refined Regularized Preference Optimization (2025)
  Pritam Sarkar et al.
  1.28
• Date Fragments: A Hidden Bottleneck of Tokenization for Temporal Reasoning (2025)
  Gagan Bhatia et al.
  1.28
• Fostering Video Reasoning via Next-Event Prediction (2025)
  Haonan Wang et al.
  1.28
• SiLVR: A Simple Language-based Video Reasoning Framework (2025)
  Ce Zhang et al.
  1.28
• VRBench: A Benchmark for Multi-Step Reasoning in Long Narrative Videos (2025)
  Jiashuo Yu et al.
  1.28
• AU-Harness: An Open-Source Toolkit for Holistic Evaluation of Audio LLMs (2025)
  Sidharth Surapaneni et al.
  1.28
• Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding (2025)
  Zaiquan Yang et al.
  1.28
• Visual Jigsaw Post-Training Improves MLLMs (2025)
  Penghao Wu et al.
  1.28
• GraphTracer: Graph-Guided Failure Tracing in LLM Agents for Robust Multi-Turn Deep Search (2025)
  Heng Zhang et al.
  1.28
• OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs (2025)
  Caorui Li et al.
  1.28
• Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment (2025)
  Kai-Po Chang et al.
  1.28
• MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding (2024)
  Xinyu Fang et al.
  —
• xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations (2024)
  Can Qin et al.
  —
• VideoLLaMB: Long-context Video Understanding with Recurrent Memory Bridges (2024)
  Yuxuan Wang et al.
  —
• NVILA: Efficient Frontier Visual Language Models (2024)
  Zhijian Liu et al.
  —