New Links | ML News

ML Newsnew | past | best | rss | submit

1981.	Practice on Long Behavior Sequence Modeling in Tencent Advertising (arxiv.org)
	1 point by PaulHoule 319 days ago \| hide \| past \| pdf \| discuss
1982.	Debiasing Reward Models by Representation Learning with Guarantees (arxiv.org)
	3 points by PaulHoule 319 days ago \| hide \| past \| pdf \| discuss
1983.	The Psychogenic Machine: Simulating AI Psychosis (arxiv.org)
	4 points by indiantinker 319 days ago \| hide \| past \| pdf \| discuss
1984.	Token embeddings violate the manifold hypothesis (arxiv.org)
	4 points by airstrike 319 days ago \| hide \| past \| pdf \| discuss
1985.	Adversarial poetry as a universal single-turn jailbreak mechanism in LLMs (arxiv.org)
	384 points by capgre 319 days ago \| hide \| past \| pdf \| 189 comments
1986.	A Style is Worth One Code: open-source Midjourey-like --sref (arxiv.org)
	2 points by meander_water 320 days ago \| hide \| past \| pdf \| discuss
1987.	DMA Collectives for Efficient ML Communication Offloads (arxiv.org)
	1 point by matt_d 320 days ago \| hide \| past \| pdf \| discuss
1988.	Slicing Is All You Need: Towards a Universal One-Sided Distributed MatMul (arxiv.org)
	99 points by matt_d 320 days ago \| hide \| past \| pdf \| 8 comments
1989.	An Agent Framework with Hardware Feedback for CUDA Kernel Optimization (arxiv.org)
	3 points by PaulHoule 320 days ago \| hide \| past \| pdf \| discuss
1990.	Semi-Supervised Preference Optimization with Limited Feedback (arxiv.org)
	2 points by PaulHoule 320 days ago \| hide \| past \| pdf \| discuss
1991.	What do you think about the Huxley Godel machine (arxiv.org)
	2 points by pranav_dhoolia 320 days ago \| hide \| past \| pdf \| 1 comment
1992.	AA-Omniscience: Evaluating Cross-Domain Knowledge Reliability in LLMs (arxiv.org)
	2 points by gmays 321 days ago \| hide \| past \| pdf \| discuss
1993.	Solving a million-step LLM task with zero errors (arxiv.org)
	222 points by Anon84 321 days ago \| hide \| past \| pdf \| 95 comments
1994.	VRScout: Towards Real-Time, Autonomous Testing of Virtual Reality Games (arxiv.org)
	2 points by PaulHoule 321 days ago \| hide \| past \| pdf \| discuss
1995.	SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing (arxiv.org)
	2 points by PaulHoule 321 days ago \| hide \| past \| pdf \| discuss
1996.	The Fundamental Limits of LLMs at Scale (arxiv.org)
	6 points by Hard_Space 321 days ago \| hide \| past \| pdf \| discuss
1997.	Nearest Neighbor Speculative Decoding for LLM Generation and Attribution (arxiv.org)
	2 points by fzliu 321 days ago \| hide \| past \| pdf \| discuss
1998.	Reliable Confidence Intervals for Information Retrieval Evaluation (arxiv.org)
	1 point by matesz 322 days ago \| hide \| past \| pdf \| discuss
1999.	Back to Basics: Let Denoising Generative Models Denoise (arxiv.org)
	4 points by dvrp 322 days ago \| hide \| past \| pdf \| discuss
2000.	AA-Omniscience: Evaluating Cross-Domain Knowledge Reliability in Language Models (arxiv.org)
	6 points by declanjackson 322 days ago \| hide \| past \| pdf \| 1 comment
2001.	LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics (arxiv.org)
	68 points by nothrowaways 322 days ago \| hide \| past \| pdf \| 18 comments
2002.	Out-of-Distribution Generalization in Transformers via Latent Space Reasoning (arxiv.org)
	9 points by marojejian 322 days ago \| hide \| past \| pdf \| 1 comment
2003.	Do Code Models Suffer from the Dunning-Kruger Effect? (arxiv.org)
	2 points by geox 322 days ago \| hide \| past \| pdf \| discuss
2004.	Towards Greater Leverage: Scaling Laws for Efficient MoE Language Models (arxiv.org)
	4 points by Anon84 322 days ago \| hide \| past \| pdf \| discuss
2005.	Attacker Moves Second: Adaptive Attacks Bypass Defenses Against LLM Jailbreaks (arxiv.org)
	3 points by Anon84 322 days ago \| hide \| past \| pdf \| discuss
2006.	TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models (arxiv.org)
	7 points by noahho 322 days ago \| hide \| past \| pdf \| discuss
2007.	Super human Stratego with RL and test time search (arxiv.org)
	2 points by algo_trader 323 days ago \| hide \| past \| pdf \| 1 comment
2008.	Stronger Adaptive Attacks Bypass Defenses Against LLM Jailbreaks (arxiv.org)
	1 point by baxtr 323 days ago \| hide \| past \| pdf \| discuss
2009.	The Era of Agentic Organization: Learning to Organize with Language Models (arxiv.org)
	1 point by nrsapt 323 days ago \| hide \| past \| pdf \| discuss
2010.	Solving a Million-Step LLM Task with Zero Errors (arxiv.org)
	2 points by meander_water 324 days ago \| hide \| past \| pdf \| 1 comment
	More