New Links | ML News

ML Newsnew | past | best | rss | submit

241.	Post-Training Language Models for Gold-Medal Performance in Coding Competitions (arxiv.org)
	2 points by sbulaev 30 days ago \| hide \| past \| pdf \| discuss
242.	Redwood: A Frontier AI Accelerator Designed from Scratch in 2 Weeks by AI (arxiv.org)
	2 points by imakwana 30 days ago \| hide \| past \| pdf \| discuss
243.	Coral: An LLM-Native Harness for Production Recommender Systems (arxiv.org)
	2 points by Anon84 30 days ago \| hide \| past \| pdf \| discuss
244.	Bandits in Prod: Hyperparameter Optimization at Inference Time (arxiv.org)
	2 points by Labo333 30 days ago \| hide \| past \| pdf \| discuss
245.	Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents (arxiv.org)
	2 points by gmays 30 days ago \| hide \| past \| pdf \| discuss
246.	Flavourbench: LLM Eval with Executable Culinary Ground Truth (arxiv.org)
	2 points by josefchen 30 days ago \| hide \| past \| pdf \| discuss
247.	Qwen-Drive-1.0 (arxiv.org)
	2 points by amancina79 30 days ago \| hide \| past \| pdf \| discuss
248.	Understanding, Mitigating Numerical Sources of Nondeterminism in LLM Inference (arxiv.org)
	1 point by shakna 30 days ago \| hide \| past \| pdf \| discuss
249.	Post-Training Language Models for Gold-Medal Performance in Coding Competitions (arxiv.org)
	1 point by oliviayii 31 days ago \| hide \| past \| pdf \| discuss
250.	Language Models Can Control Their Own Attention (arxiv.org)
	2 points by E-Reverance 31 days ago \| hide \| past \| pdf \| discuss
251.	Proper Scoring Rules Shape LLM Forecasting (arxiv.org)
	3 points by bturtel 31 days ago \| hide \| past \| pdf \| discuss
252.	LLM Judges Verify Presence, Not Absence: Omission Blindness in AI Clinical Notes (arxiv.org)
	20 points by sbulaev 31 days ago \| hide \| past \| pdf \| 14 comments
253.	What's in Your Agent's Context? Context Privilege Escalation Attacks Against AI (arxiv.org)
	1 point by sbulaev 31 days ago \| hide \| past \| pdf \| discuss
254.	BDH-CQ: In-Context Learning with Recurrent Latent Reasoning (arxiv.org)
	3 points by mdp2021 31 days ago \| hide \| past \| pdf \| 1 comment
255.	The Emergent Symbolic Structure of Artificial Neural Networks (arxiv.org)
	297 points by schmuhblaster 32 days ago \| hide \| past \| pdf \| 110 comments
256.	One in three AI scribe notes carries a verified clinical error (arxiv.org)
	2 points by sbulaev 32 days ago \| hide \| past \| pdf \| 1 comment
257.	SKILL.state: Scalable Long-Horizon Agent Skills (arxiv.org)
	1 point by Hoefner 32 days ago \| hide \| past \| pdf \| discuss
258.	Ghost Couple:Correlated LLM Name Priors Haunting the Web and Academic Publishing (arxiv.org)
	1 point by bookofjoe 32 days ago \| hide \| past \| pdf \| discuss
259.	Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090 (arxiv.org)
	3 points by simonpure 32 days ago \| hide \| past \| pdf \| discuss
260.	Can escalation channels redirect reward hacking toward defect disclosure? (arxiv.org)
	2 points by sbulaev 32 days ago \| hide \| past \| pdf \| discuss
261.	Temporal Analysis of NetFlow Datasets for Network Intrusion Detection Systems (arxiv.org)
	1 point by ENOMEM 32 days ago \| hide \| past \| pdf \| discuss
262.	Breaking Execution Continuity of Agent Systems via Rollback (arxiv.org)
	1 point by sbulaev 32 days ago \| hide \| past \| pdf \| discuss
263.	Program Learning with Verifiable Rewards: Symbolic Backpropagation (arxiv.org)
	2 points by sbulaev 33 days ago \| hide \| past \| pdf \| discuss
264.	Sliding-window beats linear attention (arxiv.org)
	2 points by simonpure 33 days ago \| hide \| past \| pdf \| 1 comment
265.	Logic and the 2-Simplicial Transformer (2019) (arxiv.org)
	2 points by wslh 33 days ago \| hide \| past \| pdf \| discuss
266.	A Policy Algebra for Trust-Preserving Agentic AI Execution (arxiv.org)
	1 point by gmays 33 days ago \| hide \| past \| pdf \| discuss
267.	Sliding-window beats linear attention (arxiv.org)
	4 points by sbulaev 33 days ago \| hide \| past \| pdf \| discuss
268.	AI Accelerator Designed, Verified, and Deployed from Scratch in 2 Weeks by AI (arxiv.org)
	2 points by Jimmc414 34 days ago \| hide \| past \| pdf \| discuss
269.	Benchmarking Confidential Computing Performance on Nvidia Blackwell GPUs (arxiv.org)
	1 point by Jimmc414 34 days ago \| hide \| past \| pdf \| discuss
270.	Static Evaluation of Model Switching in LLM Agents Scores the Wrong World (arxiv.org)
	4 points by danbitengo 34 days ago \| hide \| past \| pdf \| discuss
	More