pith. sign in

Manling Li

Identifiers

  • name variant Manling Li 0.60 · backfill

Papers (26)

  1. Behavior Uncloning: Distilling Mode Redirection into Policy Weights without Inference-Time Steering cs.RO · 2026 · author #6
  2. APT: Atomic Physical Transitions for Causal Video-Language Understanding cs.CV · 2026 · author #8
  3. SENTINEL: Failure-Driven Reinforcement Learning for Training Tool-Using Language Model Agents cs.CL · 2026 · author #9
  4. Brick-Composer: Using MLLMs for Assembly with Diverse Bricks cs.AI · 2026 · author #10
  5. BAGEN: Are LLM Agents Budget-Aware? cs.LG · 2026 · author #12
  6. Planning with the Views cs.AI · 2026 · author #10
  7. AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery cs.AI · 2026 · author #13
  8. CLORE: Content-Level Optimization for Reasoning Efficiency cs.AI · 2026 · author #6
  9. ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop cs.CV · 2026 · author #4
  10. Interactive Evaluation Requires a Design Science cs.AI · 2026 · author #9
  11. DreamAvoid: Critical-Phase Test-Time Dreaming to Avoid Failures in VLA Policies cs.RO · 2026 · author #6
  12. Using large language models for embodied planning introduces systematic safety risks cs.AI · 2026 · author #6
  13. EgoTL: Egocentric Think-Aloud Chains for Long-Horizon Tasks cs.CV · 2026 · author #10
  14. RAGEN-2: Reasoning Collapse in Agentic RL cs.LG · 2026 · author #16
  15. Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning cs.CV · 2026 · author #11
  16. Phys4D: Fine-Grained Physics-Consistent 4D Modeling from Video Diffusion cs.CV · 2026 · author #11
  17. Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs cs.LG · 2026 · author #3
  18. Towards Sparse Video Understanding and Reasoning cs.CV · 2026 · author #10
  19. Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents cs.CL · 2026 · author #13
  20. CaptionQA: Is Your Caption as Useful as the Image Itself? cs.CV · 2025 · author #7
  21. EMCompress: Video-LLMs with Endomorphic Multimodal Compression cs.CV · 2025 · author #6
  22. Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary cs.AI · 2025 · author #3
  23. RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning cs.LG · 2025 · author #18
  24. EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents cs.AI · 2025 · author #10
  25. Path-Based Attention Neural Model for Fine-Grained Entity Typing cs.CL · 2017 · author #4
  26. Efficient Parallel Translating Embedding For Knowledge Graphs cs.AI · 2017 · author #2

Mentions

  • 2606.29201 #6 · arxiv_oai · confidence 0.70 Manling Li
  • 2606.18586 #8 · arxiv_oai · confidence 0.70 Manling Li
  • 2603.03485 #11 · arxiv_oai · confidence 0.70 Manling Li
  • 2606.12908 #9 · arxiv_oai · confidence 0.70 Manling Li
  • 2606.05445 #10 · arxiv_oai · confidence 0.70 Manling Li
  • 2602.13602 #10 · arxiv_oai · confidence 0.70 Manling Li
  • 2606.00198 #12 · arxiv_oai · confidence 0.70 Manling Li
  • 2605.29563 #10 · arxiv_oai · confidence 0.70 Manling Li
  • 2602.21198 #3 · arxiv_oai · confidence 0.70 Manling Li
  • 2605.23204 #13 · arxiv_oai · confidence 0.70 Manling Li
  • 2605.22211 #6 · arxiv_oai · confidence 0.70 Manling Li
  • 2605.18746 #4 · arxiv_oai · confidence 0.70 Manling Li
  • 2605.17829 #9 · arxiv_oai · confidence 0.70 Manling Li
  • 2502.09560 #10 · arxiv_oai · confidence 0.70 Manling Li
  • 2604.09535 #10 · backfill · confidence 0.70 Manling Li

Frequent Coauthors