Natural-Language Temporal Grounding in Hour-Long Videos is a Search Problem: A Benchmark and Empirical Decomposition
Paper • 2606.12300 • Published • 1
prometheus-vision
university
AI & ML interests
None defined yet.
Recent Activity
gwkrsrch
authored a
paper 24 days ago
seungone
authored 2
papers about 1 month ago
gwkrsrch
authored 6
papers about 1 month ago
MMRefine: Unveiling the Obstacles to Robust Refinement in Multimodal Large Language Models
Paper • 2506.04688 • Published • 3
Context-Informed Grounding Supervision
Paper • 2506.15480 • Published
Does Audio Matter for Modern Video-LLMs and Their Benchmarks?
Paper • 2509.17901 • Published
MambaMia: A State-Space-Model-Based Compression for Efficient Video Understanding in Large Multimodal Models
Paper • 2506.13564 • Published
K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts
Paper • 2606.02404 • Published • 59
Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Merging
Paper • 2606.01717 • Published • 21
gwkrsrch
submitted a
paper to Daily Papers about 1 month ago
seungone
submitted a
paper to Daily Papers about 1 month ago
seungone
authored a
paper about 2 months ago
seungone
submitted a
paper to Daily Papers about 2 months ago
seungone
authored 2
papers about 2 months ago
seungone
authored 5
papers 6 months ago
Measuring Sycophancy of Language Models in Multi-turn Dialogues
Paper • 2505.23840 • Published • 4
Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
Paper • 2507.00432 • Published • 79
OptimalThinkingBench: Evaluating Over and Underthinking in LLMs
Paper • 2508.13141 • Published
VideoJudge: Bootstrapping Enables Scalable Supervision of MLLM-as-a-Judge for Video Understanding
Paper • 2509.21451 • Published
SPICE: Self-Play In Corpus Environments Improves Reasoning
Paper • 2510.24684 • Published • 18