DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents
Paper • 2608.18524 • Published • 68
Zhe Cao
MichaelCaoo
AI & ML interests
None yet
Recent Activity
upvoted a paper about 3 hours ago
DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling AgentsOrganizations
upvoted a paper about 3 hours ago
upvoted 19
papers 1 day ago
Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching
Paper • 2610.12421 • Published • 35
MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers
Paper • 2610.06801 • Published • 33
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations
Paper • 2610.01780 • Published • 278
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 • 35
OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning
Paper • 2610.12458 • Published • 12
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 • 19
VibeEdit: Image Editing with Canvas Instructions
Paper • 2610.12229 • Published • 15
Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards
Paper • 2610.02967 • Published • 26
LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation
Paper • 2610.12442 • Published • 20
SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference
Paper • 2610.12327 • Published • 25
In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks
Paper • 2609.38173 • Published • 44
AgentGarten: Code Worlds for Evolving Agents
Paper • 2610.12374 • Published • 139
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?
Paper • 2610.08215 • Published • 130
Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction
Paper • 2610.12299 • Published • 46
DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training
Paper • 2610.12468 • Published • 34
TokenRouter: Efficient Serving System for Token-Level LLM Routing
Paper • 2610.12242 • Published • 121