TrajectoryMover: Generative Movement of Object Trajectories in Videos
Paper • 2603.29092 • Published • 1
GuoLiangTang
Tommy930
AI & ML interests
LLM，NLP，ML
Recent Activity
upvoted a paper about 9 hours ago
TrajectoryMover: Generative Movement of Object Trajectories in Videos upvoted a paper about 9 hours ago
OmniRoam: World Wandering via Long-Horizon Panoramic Video Generation upvoted a paper about 9 hours ago
TokenDial: Continuous Attribute Control in Text-to-Video via Spatiotemporal Token OffsetsOrganizations
None yet
upvoted 6
papers about 9 hours ago
OmniRoam: World Wandering via Long-Horizon Panoramic Video Generation
Paper • 2603.30045 • Published • 2
TokenDial: Continuous Attribute Control in Text-to-Video via Spatiotemporal Token Offsets
Paper • 2603.27520 • Published • 2
Meta-Harness: End-to-End Optimization of Model Harnesses
Paper • 2603.28052 • Published • 4
All Roads Lead to Rome: Incentivizing Divergent Thinking in Vision-Language Models
Paper • 2604.00479 • Published • 13
Dynin-Omni: Omnimodal Unified Large Diffusion Language Model
Paper • 2604.00007 • Published • 14
upvoted 5
papers about 13 hours ago
UniMixer: A Unified Architecture for Scaling Laws in Recommendation Systems
Paper • 2604.00590 • Published • 3
Understand and Accelerate Memory Processing Pipeline for Disaggregated LLM Inference
Paper • 2603.29002 • Published • 2
Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3D Visual Grounding
Paper • 2604.00528 • Published • 4
ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners?
Paper • 2603.25823 • Published • 36
ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers
Paper • 2603.24414 • Published • 165
upvoted 6
papers about 15 hours ago
Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants
Paper • 2604.00842 • Published • 5
MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation
Paper • 2603.25406 • Published • 3
Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification
Paper • 2603.26648 • Published • 32
QuitoBench: A High-Quality Open Time Series Forecasting Benchmark
Paper • 2603.26017 • Published • 25
Terminal Agents Suffice for Enterprise Automation
Paper • 2604.00073 • Published • 65
MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome
Paper • 2603.28407 • Published • 52
upvoted 3
papers 1 day ago
FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration
Paper • 2603.29557 • Published • 12
VectorGym: A Multitask Benchmark for SVG Code Generation, Sketching, and Editing
Paper • 2603.29852 • Published • 4
CutClaw: Agentic Hours-Long Video Editing via Music Synchronization
Paper • 2603.29664 • Published • 39