New Links | ML News

ML Newsnew | past | best | rss | submit

661.	Gemma 4 Technical Report [pdf] (arxiv.org)
	3 points by theanonymousone 89 days ago \| hide \| past \| pdf \| discuss
662.	Latent Programming Horizons in Coding Agents (arxiv.org)
	3 points by andre15silva 89 days ago \| hide \| past \| pdf \| 2 comments
663.	Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injections (arxiv.org)
	1 point by _pdp_ 89 days ago \| hide \| past \| pdf \| discuss
664.	Reinforcement Learning with Metacognitive Feedback Elicits Uncertainty in LLMs (arxiv.org)
	13 points by jonnonz 89 days ago \| hide \| past \| pdf \| 1 comment
665.	Zero-Flow Encoders (arxiv.org)
	1 point by E-Reverance 89 days ago \| hide \| past \| pdf \| discuss
666.	Decomposer: Learning to Decompile Symbolic Music (Like MIDI) to Programs (arxiv.org)
	2 points by laybak 89 days ago \| hide \| past \| pdf \| discuss
667.	The Red Queen Gödel Machine: Co-Evolving Agents and Their Evaluators (arxiv.org)
	3 points by niclane7 90 days ago \| hide \| past \| pdf \| discuss
668.	Behind the Refusal: Determining Guardrail Activation via Behavioral Monitoring (arxiv.org)
	2 points by Jimmc414 90 days ago \| hide \| past \| pdf \| discuss
669.	The Hitchhiker's Guide to Agentic AI (arxiv.org)
	51 points by jonbaer 90 days ago \| hide \| past \| pdf \| 4 comments
670.	Underspecification Does Not Imply Incoherence in LLM Code Generation (arxiv.org)
	1 point by ilreb 90 days ago \| hide \| past \| pdf \| discuss
671.	Technical Report on the Pangram AI-Generated Text Classifier (2024) (arxiv.org)
	1 point by imustachyou 90 days ago \| hide \| past \| pdf \| discuss
672.	SlopCodeBench: Benchmarking How Coding Agents Degrade over Long, Iterative Tasks (arxiv.org)
	2 points by softwaredoug 90 days ago \| hide \| past \| pdf \| discuss
673.	Does code cleanliness affect coding agents? A controlled minimal-pair study (arxiv.org)
	210 points by softwaredoug 90 days ago \| hide \| past \| pdf \| 93 comments
674.	SOLAR: AI-Powered Speed-of-Light Performance Analysis (arxiv.org)
	2 points by matt_d 91 days ago \| hide \| past \| pdf \| discuss
675.	The Verification Horizon: No Silver Bullet for Coding Agent Rewards (arxiv.org)
	2 points by matt_d 91 days ago \| hide \| past \| pdf \| discuss
676.	Exploiting LLM Agent Supply Chains via Payload-Less Skills (arxiv.org)
	5 points by _pdp_ 91 days ago \| hide \| past \| pdf \| discuss
677.	How Can Reinforcement Learning Achieve Expert-Level [Chip] Placement? (arxiv.org)
	4 points by Jimmc414 92 days ago \| hide \| past \| pdf \| discuss
678.	Heterogeneous Mapping for Analog In-Memory Computing Accelerators (arxiv.org)
	2 points by Jimmc414 93 days ago \| hide \| past \| pdf \| discuss
679.	Physics informed generative AI for semiconductor manufacturing (arxiv.org)
	4 points by Jimmc414 93 days ago \| hide \| past \| pdf \| discuss
680.	Cache Merging as a Convergent Replicated State for Multi-Agent Latent Reasoning (arxiv.org)
	5 points by CarlosBaquero 93 days ago \| hide \| past \| pdf \| discuss
681.	Embodied.cpp: A Portable Inference Runtime of Embodied AI Models (arxiv.org)
	1 point by chrsw 93 days ago \| hide \| past \| pdf \| discuss
682.	Program-as-Weights: A Programming Paradigm for Fuzzy Functions (arxiv.org)
	54 points by simonpure 93 days ago \| hide \| past \| pdf \| 9 comments
683.	Explaining Attention with Program Synthesis (arxiv.org)
	2 points by GaggiX 93 days ago \| hide \| past \| pdf \| discuss
684.	Speculative pre-positioning: off-path decode for stateful inference sessions (arxiv.org)
	1 point by logotype 93 days ago \| hide \| past \| pdf \| 1 comment
685.	A Deterministic Replacement for LLM-as-Judge in Stateful Agent Evaluation (arxiv.org)
	4 points by jflynt76 93 days ago \| hide \| past \| pdf \| discuss
686.	LawZero: Safety from Honesty in a Disinterested AI Predictor (arxiv.org)
	4 points by KingKunta 93 days ago \| hide \| past \| pdf \| discuss
687.	Lean4Physics: Reasoning Framework for College Physics in Lean4 (arxiv.org)
	2 points by soupspaces 93 days ago \| hide \| past \| pdf \| discuss
688.	Manipulating Headlines in LLM-Driven Algorithmic Trading (arxiv.org)
	3 points by m-hodges 94 days ago \| hide \| past \| pdf \| 1 comment
689.	Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation (arxiv.org)
	2 points by gmays 94 days ago \| hide \| past \| pdf \| discuss
690.	Is One Layer Enough? A Single Transformer Layer Matches Full-Parameter RL Train (arxiv.org)
	153 points by tcp_handshaker 94 days ago \| hide \| past \| pdf \| 43 comments
	More