fly51fly

[CL] TRPrompt: Bootstrapping Query-Aware Prompt Optimization from Textual Rewards A Nica, I Zakazov, N M Baldwin, S Geng... [EPFL] (2025) arxiv.org/abs/2507.18618

[LG] Does visualization help AI understand data? V R. Li, J Sun, M Wattenberg [Harvard University] (2025) arxiv.org/abs/2507.18022

[LG] Revisiting LLM Reasoning via Information Bottleneck S Lei, Z Cheng, K Jia, D Tao [The University of Sydney & ByteDance] (2025) arxiv.org/abs/2507.18391

[CL] Checklists Are Better Than Reward Models For Aligning Language Models V Viswanathan, Y Sun, S Ma, X Kong... [CMU & Apple] (2025) arxiv.org/abs/2507.18624

[LG] The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm J Chen, T Hoefler, D Alistarh [ISTA & ETH Zürich] (2025) arxiv.org/abs/2507.18553

[LG] A Learning-based Domain Decomposition Method R Wu, N Kovachki, B Liu [University of Cambridge & NVIDIA ] (2025) arxiv.org/abs/2507.17328

[LG] Understanding Prompt Programming Tasks and Questions J T. Liang, C Yang, A Sergeyuk, T D. Breaux... [CMU & JetBrains Research] (2025) arxiv.org/abs/2507.17264

[CL] Can External Validation Tools Improve Annotation Quality for LLM-as-a-Judge? A Findeis, F Weers, G Yin, K Ye... [University of Cambridge & Apple] (2025) arxiv.org/abs/2507.17015

[LG] Thinking Isn't an Illusion: Overcoming the Limitations of Reasoning Models via Tool Augmentations Z Song, S Yue, J Zhang [UC Berkeley & Northeastern University] (2025) arxiv.org/abs/2507.17699

[LG] Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty M Damani, I Puri, S Slocum, I Shenfeld... [MIT] (2025) arxiv.org/abs/2507.16806

[CL] Learning without training: The implicit dynamics of in-context learning B Dherin, M Munn, H Mazzawi, M Wunder... [Google Research] (2025) arxiv.org/abs/2507.16003

[CL] Beyond Context Limits: Subconscious Threads for Long-Horizon Reasoning H Luo, N Morgan, T Li, D Zhao... [MIT CSAIL] (2025) arxiv.org/abs/2507.16784

[LG] Expert-Guided LLM Reasoning for Battery Discovery: From AI-Driven Hypothesis to Synthesis and Characterization S Liu, H Xu, Y Ai, H Li... [Universitéde Montréal & University of Oxford] (2025) arxiv.org/abs/2507.16110

[LG] From Reasoning to Super-Intelligence: A Search-Theoretic Perspective S Shalev-Shwartz, A Shashua arxiv.org/abs/2507.15865

[LG] LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models D Shi, Y Fu, X Yuan, Z Yu... [Georgia Tech] (2025) arxiv.org/abs/2507.14204

[LG] A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoning L Liu, Z Wang, L Li, C Xu... [Imperial College London & Northwestern University & University of Washington] (2025) arxiv.org/abs/2507.14295

[LG] Subliminal Learning: Language models transmit behavioral traits via hidden signals in data A Cloud, M Le, J Chua, J Betley... [Anthropic Fellows Program & Truthful AI] (2025) arxiv.org/abs/2507.14805

[LG] Inverse Scaling in Test-Time Compute A P Gema, A Hägele, R Chen, A Arditi... [University of Edinburgh & EPFL & University of Texas at Austin] (2025) arxiv.org/abs/2507.14417

[LG] The Invisible Leash: Why RLVR May Not Escape Its Origin F Wu, W Xuan, X Lu, Z Harchaoui... [Stanford University & University of Tokyo] (2025) arxiv.org/abs/2507.14843

[LG] Change of Thought: Adaptive Test-Time Computation M Mathur, M Doan, B Pearlmutter, S Plis [Google Research & Georgia State University & Maynooth University] (2025) arxiv.org/abs/2507.13569