Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching
Paper • 2610.12421 • Published • 32
Zhe Cao
MichaelCaoo
AI & ML interests
None yet
Recent Activity
upvoted a paper about 16 hours ago
Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching upvoted a paper about 16 hours ago
MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers upvoted a paper about 17 hours ago
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World ConversationsOrganizations
upvoted 2
papers about 16 hours ago
upvoted a paper about 17 hours ago
upvoted 17
papers about 19 hours ago
GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis
Paper • 2609.38923 • Published • 123
OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs
Paper • 2610.12461 • Published • 31
OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning
Paper • 2610.12458 • Published • 11
SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces
Paper • 2610.11366 • Published • 8
V-CoLA: Vision Token Compression with Linear Attention
Paper • 2610.11251 • Published • 9
OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video
Paper • 2610.12419 • Published • 16
VibeEdit: Image Editing with Canvas Instructions
Paper • 2610.12229 • Published • 13
Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards
Paper • 2610.02967 • Published • 24
LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation
Paper • 2610.12442 • Published • 18
SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference
Paper • 2610.12327 • Published • 22
In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks
Paper • 2609.38173 • Published • 41
AgentGarten: Code Worlds for Evolving Agents
Paper • 2610.12374 • Published • 131
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?
Paper • 2610.08215 • Published • 86
Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction
Paper • 2610.12299 • Published • 43
DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training
Paper • 2610.12468 • Published • 33
TokenRouter: Efficient Serving System for Token-Level LLM Routing
Paper • 2610.12242 • Published • 104
SuperNav: An Agentic Navigation System for Any Task in Any Scene
Paper • 2610.12126 • Published • 63