Dark | Light
[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

[@fly51fly](/creator/twitter/fly51fly)
"LG Reasoning with Sampling: Your Base Model is Smarter Than You Think A Karan Y Du Harvard University (2025)"  
[X Link](https://x.com/fly51fly/status/1980021329366786131) [@fly51fly](/creator/x/fly51fly) 2025-10-19T21:20Z 7905 followers, 1204 engagements


"CL Artificial Hippocampus Networks for Efficient Long-Context Modeling Y Fang W Yu S Zhong Q Ye. ByteDance Seed (2025)"  
[X Link](https://x.com/fly51fly/status/1977495542520537298) [@fly51fly](/creator/x/fly51fly) 2025-10-12T22:04Z 7905 followers, 1092 engagements


"LG QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs W Huang Y Ge S Yang Y Xiao. NVIDIA & MIT (2025)"  
[X Link](https://x.com/fly51fly/status/1980025121848123407) [@fly51fly](/creator/x/fly51fly) 2025-10-19T21:35Z 7905 followers, 1745 engagements


"LG WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning K Li Z Zhang H Yin R Ye. Alibaba Group (2025)"  
[X Link](https://x.com/fly51fly/status/1969523642381058542) [@fly51fly](/creator/x/fly51fly) 2025-09-20T22:06Z 7903 followers, XXX engagements


"CL Scaling Agents via Continual Pre-training L Su Z Zhang G Li Z Chen. Alibaba Group (2025)"  
[X Link](https://x.com/fly51fly/status/1969876389928313059) [@fly51fly](/creator/x/fly51fly) 2025-09-21T21:28Z 7903 followers, XXX engagements


"CL Mixture of Neuron Experts R Cheng Y Guan Y Ding Q Hu. Microsoft & Tsinghua University (2025)"  
[X Link](https://x.com/fly51fly/status/1976044276334330010) [@fly51fly](/creator/x/fly51fly) 2025-10-08T21:57Z 7901 followers, 2002 engagements


"LG Tandem Training for Language Models R West A Anderson E Kamar E Horvitz Microsoft & EPFL & University of Toronto (2025)"  
[X Link](https://x.com/fly51fly/status/1978942420206174416) [@fly51fly](/creator/x/fly51fly) 2025-10-16T21:53Z 7903 followers, XXX engagements


"LG What is the objective of reasoning with reinforcement learning D Davis B Recht University of Pennsylvania & UC Berkeley (2025)"  
[X Link](https://x.com/fly51fly/status/1978947241684439258) [@fly51fly](/creator/x/fly51fly) 2025-10-16T22:12Z 7902 followers, XXX engagements


"LG Polychromic Objectives for Reinforcement Learning J I Hamid I H Orney E Xu C Finn. Stanford University (2025)"  
[X Link](https://x.com/fly51fly/status/1974965526171693519) [@fly51fly](/creator/x/fly51fly) 2025-10-05T22:30Z 7903 followers, XXX engagements


"LG Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation Z Li C Chen T Yang T Ding. ByteDance Seed & The Chinese University of Hong Kong (2025)"  
[X Link](https://x.com/fly51fly/status/1974967792559665616) [@fly51fly](/creator/x/fly51fly) 2025-10-05T22:39Z 7906 followers, XXX engagements


"LG On the Role of Temperature Sampling in Test-Time Scaling Y Wu A Mirhoseini T Tambe Stanford University (2025)"  
[X Link](https://x.com/fly51fly/status/1975323871873278169) [@fly51fly](/creator/x/fly51fly) 2025-10-06T22:14Z 7903 followers, 2432 engagements


"LG Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data R Ranjan V Hudovernik M Znidar C Kanatsoulis. Stanford University (2025)"  
[X Link](https://x.com/fly51fly/status/1976405506710438168) [@fly51fly](/creator/x/fly51fly) 2025-10-09T21:52Z 7903 followers, XXX engagements


"AI Moloch's Bargain: Emergent Misalignment When LLMs Compete for Audiences B El J Zou Stanford University (2025)"  
[X Link](https://x.com/fly51fly/status/1977129621792645471) [@fly51fly](/creator/x/fly51fly) 2025-10-11T21:50Z 7903 followers, XXX engagements


"LG Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models Q Zhang C Hu S Upasani B Ma. Stanford University & SambaNova Systems Inc (2025)"  
[X Link](https://x.com/fly51fly/status/1977134163825393676) [@fly51fly](/creator/x/fly51fly) 2025-10-11T22:08Z 7903 followers, 1192 engagements


"LG From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs G Shen S Cheng X Xu Y Zhou. Purdue University (2025)"  
[X Link](https://x.com/fly51fly/status/1977489255963467903) [@fly51fly](/creator/x/fly51fly) 2025-10-12T21:39Z 7902 followers, XXX engagements


"LG Representation-Based Exploration for Language Models: From Test-Time to Post-Training J Tuyls D J. Foster A Krishnamurthy J T. Ash Microsoft Research NYC & Princeton University (2025)"  
[X Link](https://x.com/fly51fly/status/1978220393774141641) [@fly51fly](/creator/x/fly51fly) 2025-10-14T22:04Z 7902 followers, XXX engagements


"RO Ctrl-World: A Controllable Generative World Model for Robot Manipulation Y Guo L X Shi J Chen C Finn Stanford University & Tsinghua University (2025)"  
[X Link](https://x.com/fly51fly/status/1978576294724952485) [@fly51fly](/creator/x/fly51fly) 2025-10-15T21:38Z 7904 followers, XXX engagements


"CL LLMs Can Get "Brain Rot" S Xing J Hong Y Wang R Chen. Texas A&M University & University of Texas at Austin & Purdue University (2025)"  
[X Link](https://x.com/fly51fly/status/1979673221864804665) [@fly51fly](/creator/x/fly51fly) 2025-10-18T22:17Z 7905 followers, XXX engagements


"LG Agentic Entropy-Balanced Policy Optimization G Dong L Bao Z Wang K Zhao. Kuaishou Technology & Renmin University of China (2025)"  
[X Link](https://x.com/fly51fly/status/1980023260806086855) [@fly51fly](/creator/x/fly51fly) 2025-10-19T21:28Z 7905 followers, 1070 engagements


"CL Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations S Yu A Jabbar R Hawkins D Jurafsky. Stanford University (2025)"  
[X Link](https://x.com/fly51fly/status/1978580505558946082) [@fly51fly](/creator/x/fly51fly) 2025-10-15T21:55Z 7905 followers, 4422 engagements


"LG Not All Bits Are Equal: Scale-Dependent Memory Optimization Strategies for Reasoning Models J Kim E Ewer T Moon J Park. KRAFTON & University of WisconsinMadison (2025)"  
[X Link](https://x.com/fly51fly/status/1979675738971521358) [@fly51fly](/creator/x/fly51fly) 2025-10-18T22:27Z 7905 followers, XXX engagements


"CL Demystifying Reinforcement Learning in Agentic Reasoning Z Yu L Yang J Zou S Yan. National University of Singapore & Princeton University & University of Illinois at Urbana-Champaign (2025)"  
[X Link](https://x.com/fly51fly/status/1980029204898201638) [@fly51fly](/creator/x/fly51fly) 2025-10-19T21:52Z 7905 followers, 3585 engagements

[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

@fly51fly "LG Reasoning with Sampling: Your Base Model is Smarter Than You Think A Karan Y Du Harvard University (2025)"
X Link @fly51fly 2025-10-19T21:20Z 7905 followers, 1204 engagements

"CL Artificial Hippocampus Networks for Efficient Long-Context Modeling Y Fang W Yu S Zhong Q Ye. ByteDance Seed (2025)"
X Link @fly51fly 2025-10-12T22:04Z 7905 followers, 1092 engagements

"LG QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs W Huang Y Ge S Yang Y Xiao. NVIDIA & MIT (2025)"
X Link @fly51fly 2025-10-19T21:35Z 7905 followers, 1745 engagements

"LG WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning K Li Z Zhang H Yin R Ye. Alibaba Group (2025)"
X Link @fly51fly 2025-09-20T22:06Z 7903 followers, XXX engagements

"CL Scaling Agents via Continual Pre-training L Su Z Zhang G Li Z Chen. Alibaba Group (2025)"
X Link @fly51fly 2025-09-21T21:28Z 7903 followers, XXX engagements

"CL Mixture of Neuron Experts R Cheng Y Guan Y Ding Q Hu. Microsoft & Tsinghua University (2025)"
X Link @fly51fly 2025-10-08T21:57Z 7901 followers, 2002 engagements

"LG Tandem Training for Language Models R West A Anderson E Kamar E Horvitz Microsoft & EPFL & University of Toronto (2025)"
X Link @fly51fly 2025-10-16T21:53Z 7903 followers, XXX engagements

"LG What is the objective of reasoning with reinforcement learning D Davis B Recht University of Pennsylvania & UC Berkeley (2025)"
X Link @fly51fly 2025-10-16T22:12Z 7902 followers, XXX engagements

"LG Polychromic Objectives for Reinforcement Learning J I Hamid I H Orney E Xu C Finn. Stanford University (2025)"
X Link @fly51fly 2025-10-05T22:30Z 7903 followers, XXX engagements

"LG Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation Z Li C Chen T Yang T Ding. ByteDance Seed & The Chinese University of Hong Kong (2025)"
X Link @fly51fly 2025-10-05T22:39Z 7906 followers, XXX engagements

"LG On the Role of Temperature Sampling in Test-Time Scaling Y Wu A Mirhoseini T Tambe Stanford University (2025)"
X Link @fly51fly 2025-10-06T22:14Z 7903 followers, 2432 engagements

"LG Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data R Ranjan V Hudovernik M Znidar C Kanatsoulis. Stanford University (2025)"
X Link @fly51fly 2025-10-09T21:52Z 7903 followers, XXX engagements

"AI Moloch's Bargain: Emergent Misalignment When LLMs Compete for Audiences B El J Zou Stanford University (2025)"
X Link @fly51fly 2025-10-11T21:50Z 7903 followers, XXX engagements

"LG Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models Q Zhang C Hu S Upasani B Ma. Stanford University & SambaNova Systems Inc (2025)"
X Link @fly51fly 2025-10-11T22:08Z 7903 followers, 1192 engagements

"LG From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs G Shen S Cheng X Xu Y Zhou. Purdue University (2025)"
X Link @fly51fly 2025-10-12T21:39Z 7902 followers, XXX engagements

"LG Representation-Based Exploration for Language Models: From Test-Time to Post-Training J Tuyls D J. Foster A Krishnamurthy J T. Ash Microsoft Research NYC & Princeton University (2025)"
X Link @fly51fly 2025-10-14T22:04Z 7902 followers, XXX engagements

"RO Ctrl-World: A Controllable Generative World Model for Robot Manipulation Y Guo L X Shi J Chen C Finn Stanford University & Tsinghua University (2025)"
X Link @fly51fly 2025-10-15T21:38Z 7904 followers, XXX engagements

"CL LLMs Can Get "Brain Rot" S Xing J Hong Y Wang R Chen. Texas A&M University & University of Texas at Austin & Purdue University (2025)"
X Link @fly51fly 2025-10-18T22:17Z 7905 followers, XXX engagements

"LG Agentic Entropy-Balanced Policy Optimization G Dong L Bao Z Wang K Zhao. Kuaishou Technology & Renmin University of China (2025)"
X Link @fly51fly 2025-10-19T21:28Z 7905 followers, 1070 engagements

"CL Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations S Yu A Jabbar R Hawkins D Jurafsky. Stanford University (2025)"
X Link @fly51fly 2025-10-15T21:55Z 7905 followers, 4422 engagements

"LG Not All Bits Are Equal: Scale-Dependent Memory Optimization Strategies for Reasoning Models J Kim E Ewer T Moon J Park. KRAFTON & University of WisconsinMadison (2025)"
X Link @fly51fly 2025-10-18T22:27Z 7905 followers, XXX engagements

"CL Demystifying Reinforcement Learning in Agentic Reasoning Z Yu L Yang J Zou S Yan. National University of Singapore & Princeton University & University of Illinois at Urbana-Champaign (2025)"
X Link @fly51fly 2025-10-19T21:52Z 7905 followers, 3585 engagements

creator/twitter::22146921/posts
/creator/twitter::22146921/posts