RSIHub: A Composable Framework for Agent-Evolution Methods
Paper • 2610.32253 • Published • 39
Yiming Qu
y-m-qu
·
AI & ML interests
BM25 + neural + index compression + multi-hop QA
Recent Activity
upvoted a paper about 7 hours ago
RSIHub: A Composable Framework for Agent-Evolution Methods upvoted a paper about 7 hours ago
RynnUnify: Towards Unified Embodied Brain upvoted a paper about 7 hours ago
Generalized CycleGRPO for Fine-Grained Multimodal Understanding and GroundingOrganizations
None yet
upvoted 5
papers about 7 hours ago
RynnUnify: Towards Unified Embodied Brain
Paper • 2610.32965 • Published • 44
Generalized CycleGRPO for Fine-Grained Multimodal Understanding and Grounding
Paper • 2610.29552 • Published • 8
HiSTEVE 1.0: Harnessing Human-Interface VLA Agents for Open-World Games
Paper • 2610.31162 • Published • 46
Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs
Paper • 2610.27103 • Published • 33
upvoted 3
papers 1 day ago
HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents
Paper • 2610.23479 • Published • 125
Specter: Fast MoE Inference via Quantization-Enabled Multi-Step Speculative Offloading
Paper • 2511.14102 • Published • 27
Spectral-Spatial Interpretation
Paper • 2610.21114 • Published • 756
upvoted 4
papers 3 days ago
EvaOmni: An Evidence-Grounded Benchmark for Audio-Visual Reasoning
Paper • 2610.28444 • Published • 28
SimVTA: Simulation-Grounded Video-Trajectory Alignment for Driving World Action Models
Paper • 2610.13781 • Published • 32
MT Forcing: Towards Stable and Consistent Multi-Turn Image Editing with Autoregressive Diffusion
Paper • 2610.25404 • Published • 48
Answering in the User's Variety: Calibrated Accommodation Pairs for Post-Training
Paper • 2610.28474 • Published • 16
upvoted 2
papers 4 days ago
upvoted 5
papers 5 days ago
RoAR-VAE: Improving Latent Diffusability through Robust Prediction
Paper • 2610.26216 • Published • 42
MemT-1.0: Towards Memory-Native Evolution
Paper • 2610.26825 • Published • 183
Interlock: From Local Correctness to Task Completion in Long-Horizon Agents
Paper • 2610.19686 • Published • 50
OR-License: Evaluating LLM Agents as Real-World Operations Research Practitioners
Paper • 2610.24087 • Published • 58
AdaExploreBench: Benchmarking LLM Agents for Proactive Exploration and Test-time Adaptation in Evolving Environments
Paper • 2610.25950 • Published • 38
upvoted a paper 6 days ago