Papers - 2026-10-08
吾能观之数千而面色如故
views
| comments
Grounding-driven Visual Reasoning#
3D LLM#
From Evidence to Action: How Tool-Using Agents Fail
No summary available.
AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents
No summary available.
MiniCorp: The Last Mile of the AI Agent Firm
No summary available.
Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents
No summary available.
Multimodal World Model#
Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability
No summary available.
TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models
No summary available.
DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation
No summary available.
Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing
No summary available.
HuatuoGPT-3: RL-Only Domain Adaptation from Base Models
No summary available.
World Action Learning via Interaction-Centric Spectral Latent Guidance
No summary available.
UNREAL: Unifying Retrieval and Long-Context with a Single Model
No summary available.