Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning
Paper • 2606.10968 • Published • 41
AI & ML interests
None defined yet.
Recent Activity
View all activity
zhouxiangxin
submitted a
paper to Daily Papers about 9 hours ago
zhouxiangxin
submitted a
paper to Daily Papers 1 day ago
Jiaqi-hkust
posted an update 3 days ago
Post
3442
Happy to introduce Response-G1 #ACL2026 — a proactive agent for streaming video understanding.
📄 Paper: http://arxiv.org/abs/2605.07575
📷 Code: http://github.com/kadmkbl/Response-G1
We are happy to have a further discussion!!!
#ACL2026 #AI #Multimodal #VideoUnderstanding #OpenSource #LLM
📄 Paper: http://arxiv.org/abs/2605.07575
📷 Code: http://github.com/kadmkbl/Response-G1
We are happy to have a further discussion!!!
#ACL2026 #AI #Multimodal #VideoUnderstanding #OpenSource #LLM
- 1 reply
FlippyDora
authored 5
papers about 2 months ago
EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents
Paper • 2412.13549 • Published
GAR: Generative Adversarial Reinforcement Learning for Formal Theorem Proving
Paper • 2510.11769 • Published • 26
ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning
Paper • 2510.12693 • Published • 28
Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models
Paper • 2603.13985 • Published • 11
AgentSPEX: An Agent SPecification and EXecution Language
Paper • 2604.13346 • Published • 164
Jiaqi-hkust
posted an update 3 months ago
Post
5870
🛰️ Introducing Awesome-Remote-Sensing-Agents: The Largest Curated Collection of Intelligent Remote Sensing Agents
We are excited to share our new repository Awesome-Remote-Sensing-Agents – a comprehensive, community-driven collection of 100+ papers at the intersection of remote sensing and intelligent agents (LLMs, VLM, multi‑agent systems, etc.).
🔗 GitHub Repository: https://github.com/PolyX-Research/Awesome-Remote-Sensing-Agents
Our repository organizes this rapidly growing field into a structured, easy‑to‑navigate resource for researchers, practitioners, and enthusiasts.
📚 What’s Inside?
We’ve carefully curated papers across 6 key application domains:
🌿 Ecological Monitoring – forest fires, biodiversity, climate science
🚨 Emergency Response – flood mapping, wildfire tracking, disaster geolocalization
⛏️ Geological Exploration – mineral mapping, lithological recognition, geologic reasoning
🌊 Marine Supervision – ocean science, autonomous surface vehicles
🌾 Precision Agriculture – crop disease detection, land use simulation
🏙️ Urban Governance – change detection, urban planning, embodied navigation
🤝 Join the Community!
We warmly welcome contributions to keep this list up‑to‑date:
📝 Add missing papers via Pull Request
🏷️ Propose new or refined categories
🔗 Report broken links or outdated entries
💬 Discuss via GitHub Issues or contact the authors
We are excited to share our new repository Awesome-Remote-Sensing-Agents – a comprehensive, community-driven collection of 100+ papers at the intersection of remote sensing and intelligent agents (LLMs, VLM, multi‑agent systems, etc.).
🔗 GitHub Repository: https://github.com/PolyX-Research/Awesome-Remote-Sensing-Agents
Our repository organizes this rapidly growing field into a structured, easy‑to‑navigate resource for researchers, practitioners, and enthusiasts.
📚 What’s Inside?
We’ve carefully curated papers across 6 key application domains:
🌿 Ecological Monitoring – forest fires, biodiversity, climate science
🚨 Emergency Response – flood mapping, wildfire tracking, disaster geolocalization
⛏️ Geological Exploration – mineral mapping, lithological recognition, geologic reasoning
🌊 Marine Supervision – ocean science, autonomous surface vehicles
🌾 Precision Agriculture – crop disease detection, land use simulation
🏙️ Urban Governance – change detection, urban planning, embodied navigation
🤝 Join the Community!
We warmly welcome contributions to keep this list up‑to‑date:
📝 Add missing papers via Pull Request
🏷️ Propose new or refined categories
🔗 Report broken links or outdated entries
💬 Discuss via GitHub Issues or contact the authors
FlippyDora
submitted a
paper to Daily Papers 3 months ago
zhouxiangxin
authored a
paper 4 months ago
FlippyDora
authored a
paper 5 months ago
FlippyDora
submitted a
paper to Daily Papers 5 months ago
xiuhuywh
authored a
paper 5 months ago
Jiaqi-hkust
authored a
paper 6 months ago
Jiaqi-hkust
submitted a
paper to Daily Papers 6 months ago
Jiaqi-hkust
posted an update 6 months ago
Post
3711
We have open-sourced Robust-R1 (AAAI 2026 Oral), a new paradigm in the field of anti-degradation and robustness enhancement for multimodal large models.
Multimodal Large Language Models struggle to maintain reliable performance under extreme real-world visual degradations, which impede their practical robustness. Existing robust MLLMs predominantly rely on implicit training/adaptation that focuses solely on visual encoder generalization, suffering from limited interpretability and isolated optimization. To overcome these limitations, we propose Robust-R1, a novel framework that explicitly models visual degradations through structured reasoning chains. Our approach integrates: (i) supervised fine-tuning for degradation-aware reasoning foundations, (ii) reward-driven alignment for accurately perceiving degradation parameters, and (iii) dynamic reasoning depth scaling adapted to degradation intensity. To facilitate this approach, we introduce a specialized 11K dataset featuring realistic degradations synthesized across four critical real-world visual processing stages, each annotated with structured chains connecting degradation parameters, perceptual influence, pristine semantic reasoning chain, and conclusion. Comprehensive evaluations demonstrate state-of-the-art robustness: Robust-R1 outperforms all general and robust baselines on the real-world degradation benchmark R-Bench, while maintaining superior anti-degradation performance under multi-intensity adversarial degradations on MMMB, MMStar, and RealWorldQA.
We have made all of our papers, codes, data, model weights and demos fully open-source:
Paper: Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding (2512.17532) (help us to upvote)
GitHub code: https://github.com/jqtangust/Robust-R1 (help us to star)
HF model: https://huggingface.co/Jiaqi-hkust/Robust-R1
HF data: Jiaqi-hkust/Robust-R1
HF Space: Jiaqi-hkust/Robust-R1
We sincerely invite everyone to give it a try.
Multimodal Large Language Models struggle to maintain reliable performance under extreme real-world visual degradations, which impede their practical robustness. Existing robust MLLMs predominantly rely on implicit training/adaptation that focuses solely on visual encoder generalization, suffering from limited interpretability and isolated optimization. To overcome these limitations, we propose Robust-R1, a novel framework that explicitly models visual degradations through structured reasoning chains. Our approach integrates: (i) supervised fine-tuning for degradation-aware reasoning foundations, (ii) reward-driven alignment for accurately perceiving degradation parameters, and (iii) dynamic reasoning depth scaling adapted to degradation intensity. To facilitate this approach, we introduce a specialized 11K dataset featuring realistic degradations synthesized across four critical real-world visual processing stages, each annotated with structured chains connecting degradation parameters, perceptual influence, pristine semantic reasoning chain, and conclusion. Comprehensive evaluations demonstrate state-of-the-art robustness: Robust-R1 outperforms all general and robust baselines on the real-world degradation benchmark R-Bench, while maintaining superior anti-degradation performance under multi-intensity adversarial degradations on MMMB, MMStar, and RealWorldQA.
We have made all of our papers, codes, data, model weights and demos fully open-source:
Paper: Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding (2512.17532) (help us to upvote)
GitHub code: https://github.com/jqtangust/Robust-R1 (help us to star)
HF model: https://huggingface.co/Jiaqi-hkust/Robust-R1
HF data: Jiaqi-hkust/Robust-R1
HF Space: Jiaqi-hkust/Robust-R1
We sincerely invite everyone to give it a try.
- 2 replies
Jiaqi-hkust
authored a
paper 6 months ago
Jiaqi-hkust
submitted a
paper to Daily Papers 6 months ago
Jiaqi-hkust
authored a
paper 6 months ago