Beyond Watching and Searching: Benchmarking Agents for Video-centered Deep Research Reports
Paper • 2610.31158 • Published • 17
👋 Open to Work
Yiming Zhao
gaotiexinqu
AI & ML interests
VLMs, Agent, RL, Reasoning
Recent Activity
upvoted a paper 19 days ago
GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis authored a paper 3 months ago
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch AgentOrganizations
upvoted a paper 1 day ago
upvoted a paper 19 days ago
upvoted a paper 3 months ago
upvoted 4
papers 5 months ago
AsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task Scenarios
Paper • 2605.27995 • Published • 12
SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering
Paper • 2605.17526 • Published • 7
VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation
Paper • 2605.16079 • Published • 13
OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation
Paper • 2605.12480 • Published • 4
upvoted 3
papers 6 months ago
SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation
Paper • 2605.08043 • Published • 10
Flow-OPD: On-Policy Distillation for Flow Matching Models
Paper • 2605.08063 • Published • 73
SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents
Paper • 2604.17308 • Published • 23
upvoted 3
papers 9 months ago
Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models
Paper • 2601.22060 • Published • 117
Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models
Paper • 2602.02185 • Published • 106
V2P-Bench: Evaluating Video-Language Understanding with Visual Prompts for Better Human-Model Interaction
Paper • 2503.17736 • Published • 3
upvoted a paper over 1 year ago