New Links | ML News

ML Newsnew | past | best | rss | submit

31.	Pluralis Towards a Multicultural Multimodal, Multilingual Benchmark for AI Risk (arxiv.org)
	1 point by thinkevolve 4 days ago \| hide \| past \| pdf \| discuss
32.	AmpleGCG: Learning a Universal Generative Model for Jailbreaking (arxiv.org)
	1 point by Anon84 4 days ago \| hide \| past \| pdf \| discuss
33.	Schedules Are Solvable Symbols: Tuning-Free Compilation of Tile Programs (arxiv.org)
	2 points by matt_d 4 days ago \| hide \| past \| pdf \| discuss
34.	Learning How to Forget: Fine-Tuning for Long-Context Sparse Attention (arxiv.org)
	1 point by theanonymousone 4 days ago \| hide \| past \| pdf \| discuss
35.	Fathom: Per-query read depth for sparse decoding over offloaded KV caches (arxiv.org)
	1 point by vivekkalyanaran 4 days ago \| hide \| past \| pdf \| discuss
36.	Netflix replaced their recommendation algorithm with an LLM (arxiv.org)
	2 points by nreece 4 days ago \| hide \| past \| pdf \| 1 comment
37.	Self-Play Pretraining with Zero Data (arxiv.org)
	3 points by 7777777phil 4 days ago \| hide \| past \| pdf \| discuss
38.	Shockingly Simple Self-retrospection Improves Agentic Models Without RL (arxiv.org)
	2 points by Betelbuddy 4 days ago \| hide \| past \| pdf \| discuss
39.	Language Models Act on Hidden Valence (arxiv.org)
	2 points by sbulaev 4 days ago \| hide \| past \| pdf \| discuss
40.	User Model Extraction via Belief Self-Distillation (arxiv.org)
	1 point by sbulaev 4 days ago \| hide \| past \| pdf \| discuss
41.	CORVUS: Context Optimization and Reduction via Underlying Synchronization (arxiv.org)
	2 points by matt_d 5 days ago \| hide \| past \| pdf \| discuss
42.	An Internet for the KV Cache: Rethinking Classical Infrastructure Boundaries (arxiv.org)
	2 points by matt_d 5 days ago \| hide \| past \| pdf \| discuss
43.	GenRec: An LLM-Backed Recommendation Ranker at NetflixConference (arxiv.org)
	3 points by throwthrowrow 5 days ago \| hide \| past \| pdf \| discuss
44.	EnigmaForge – an LLM benchmark where the question is hidden in the story (arxiv.org)
	1 point by robottwo 5 days ago \| hide \| past \| pdf \| discuss
45.	Recursive Self-Improvement via On-Policy Distillation for Reasoning (arxiv.org)
	2 points by simonpure 5 days ago \| hide \| past \| pdf \| discuss
46.	A-Mem: Agentic Memory for LLM Agents (arxiv.org)
	2 points by jerlendds 5 days ago \| hide \| past \| pdf \| discuss
47.	CliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents (arxiv.org)
	1 point by 6bitquant 5 days ago \| hide \| past \| pdf \| discuss
48.	Foundations of Large Language Models (arxiv.org)
	3 points by rramadass 5 days ago \| hide \| past \| pdf \| 1 comment
49.	Open-Source E2E FHE Implementation for Privacy-Preserving Llama 3 8B Inference (arxiv.org)
	2 points by simonpure 6 days ago \| hide \| past \| pdf \| discuss
50.	TuxBot: Semantic-Aware Online OS Tuning with Large Language Models (arxiv.org)
	1 point by matt_d 6 days ago \| hide \| past \| pdf \| discuss
51.	Quantized Reasoning Models Think They Need to Think Longer, but They Do Not (arxiv.org)
	13 points by theanonymousone 6 days ago \| hide \| past \| pdf \| 1 comment
52.	"As a Language Model": Chat Template Switches LLM Self-Referential Voice (arxiv.org)
	103 points by yu3zhou4 6 days ago \| hide \| past \| pdf \| 110 comments
53.	LLM Agents Can Easily Tamper with Their Own Traces (arxiv.org)
	3 points by sbulaev 6 days ago \| hide \| past \| pdf \| 1 comment
54.	Just Ask Jev: Reinforcement Learning for Calibrated Decisions (arxiv.org)
	1 point by Anon84 7 days ago \| hide \| past \| pdf \| discuss
55.	DeepSeek Elastic Compute (DSec) (arxiv.org)
	323 points by shenli3514 7 days ago \| hide \| past \| pdf \| 116 comments
56.	Grow the Harness, Not the Context (arxiv.org)
	1 point by acossta 7 days ago \| hide \| past \| pdf \| discuss
57.	Codetta: High-Capacity, Keyless, and Undetectable Multi-Agent Collusion (arxiv.org)
	1 point by sbulaev 7 days ago \| hide \| past \| pdf \| discuss
58.	What and Whose Knowledge? Measuring Epistemic Diversity in Large Language Models (arxiv.org)
	2 points by daniel_iversen 7 days ago \| hide \| past \| pdf \| discuss
59.	Transformer Can Hold Two Thoughts at Once: Evidence of Linear (arxiv.org)
	3 points by sbulaev 7 days ago \| hide \| past \| pdf \| discuss
60.	Skill-Guided Mining and Compilation of LLM Agent Traces (arxiv.org)
	1 point by nlpnerd 8 days ago \| hide \| past \| pdf \| discuss
	More