New Links | ML News

ML Newsnew | past | best | rss | submit

1291.	Reasoning-Based Personalized Generation for Users with Sparse Data (arxiv.org)
	3 points by PaulHoule 191 days ago \| hide \| past \| pdf \| discuss
1292.	TinyLoRA – Learning to Reason in 13 Parameters (arxiv.org)
	234 points by sorenjan 191 days ago \| hide \| past \| pdf \| 45 comments
1293.	Agentic Context Engineering: Evolving Contexts for Self-Improving Language Model (arxiv.org)
	3 points by Anon84 192 days ago \| hide \| past \| pdf \| 1 comment
1294.	An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU (arxiv.org)
	3 points by matt_d 192 days ago \| hide \| past \| pdf \| discuss
1295.	Are LLMs Reliable Code Reviewers? (arxiv.org)
	3 points by PaulHoule 192 days ago \| hide \| past \| pdf \| discuss
1296.	Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents (arxiv.org)
	3 points by brandonb 192 days ago \| hide \| past \| pdf \| discuss
1297.	LeWorldModel: Stable E2E Joint-Embedding Predictive Architecture from Pixels (arxiv.org)
	2 points by mpweiher 192 days ago \| hide \| past \| pdf \| discuss
1298.	Nemotron-Cascade 2: Post-Training LLMs with Cascade RL, On-Policy Distillation (arxiv.org)
	2 points by gmays 192 days ago \| hide \| past \| pdf \| discuss
1299.	Paper: Reducing hallucination in English–Hindi LLMs using citation grounding (arxiv.org)
	1 point by vedantpandya 193 days ago \| hide \| past \| pdf \| discuss
1300.	ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases (arxiv.org)
	2 points by BalinKing 193 days ago \| hide \| past \| pdf \| discuss
1301.	Google's extreme AI compression paper was on arXiv since April 2025 (arxiv.org)
	2 points by fadijob 193 days ago \| hide \| past \| pdf \| 1 comment
1302.	Expert Personas Improve LLM Alignment but Damage Accuracy (arxiv.org)
	1 point by inaros 193 days ago \| hide \| past \| pdf \| discuss
1303.	LeWorldModel with Yann LeCun (arxiv.org)
	2 points by guerby 193 days ago \| hide \| past \| pdf \| 1 comment
1304.	VTAM: Video-Tactile-Action Models for Complex Physical Interaction Beyond VLAs (arxiv.org)
	1 point by chrsw 194 days ago \| hide \| past \| pdf \| discuss
1305.	Generalized Discrete Diffusion from Snapshots (arxiv.org)
	1 point by GaggiX 194 days ago \| hide \| past \| pdf \| discuss
1306.	PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost (arxiv.org)
	2 points by matt_d 194 days ago \| hide \| past \| pdf \| discuss
1307.	DeepSeek: Conditional Memory via Scalable Lookup (arxiv.org)
	7 points by born-jre 194 days ago \| hide \| past \| pdf \| discuss
1308.	InterviewSim: A Scalable Framework for Interview-Grounded Personality Simulation (arxiv.org)
	2 points by PaulHoule 194 days ago \| hide \| past \| pdf \| discuss
1309.	Hyperagents (arxiv.org)
	3 points by mococa 194 days ago \| hide \| past \| pdf \| discuss
1310.	AI Agents Can Autonomously Perform Experimental High Energy Physics (arxiv.org)
	3 points by KolenCh 195 days ago \| hide \| past \| pdf \| 1 comment
1311.	Expert Personas Improve LLM Alignment but Damage Accuracy (arxiv.org)
	1 point by Jacques2Marais 195 days ago \| hide \| past \| pdf \| discuss
1312.	OpenMath: Ontology-Guided Neuro-Symbolic Inference (arxiv.org)
	3 points by marcelolabre 195 days ago \| hide \| past \| pdf \| 1 comment
1313.	LUMINA: LLM-Guided GPU Architecture Exploration via Bottleneck Analysis (arxiv.org)
	3 points by matt_d 195 days ago \| hide \| past \| pdf \| discuss
1314.	An agent autonomously builds a 1.5 GHz Linux-capable RISC-V CPU (arxiv.org)
	4 points by fork-bomber 195 days ago \| hide \| past \| pdf \| discuss
1315.	Hyperagents (arxiv.org)
	3 points by handfuloflight 195 days ago \| hide \| past \| pdf \| discuss
1316.	An Introduction to Probabilistic Programming (2018) (arxiv.org)
	2 points by fagnerbrack 195 days ago \| hide \| past \| pdf \| discuss
1317.	Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search (arxiv.org)
	3 points by limoce 196 days ago \| hide \| past \| pdf \| discuss
1318.	The Artificial Self: Characterising the Landscape of AI Identity (arxiv.org)
	2 points by est 196 days ago \| hide \| past \| pdf \| discuss
1319.	Secure Linear Alignment of Large Language Models (arxiv.org)
	2 points by walterbell 196 days ago \| hide \| past \| pdf \| 1 comment
1320.	Whole-Brain Connectomic Graph Model Enables Locomotion Control in Fruit Fly (arxiv.org)
	2 points by maxloh 196 days ago \| hide \| past \| pdf \| discuss
	More