New Links | ML News

ML Newsnew | past | best | rss | submit

181.	You Only Cache Once: Decoder-Decoder Architectures for Language Models (2024) (arxiv.org)
	1 point by theanonymousone 22 days ago \| hide \| past \| pdf \| discuss
182.	Cross-Lingual Alignment Without Joint Training (arxiv.org)
	1 point by codelion 22 days ago \| hide \| past \| pdf \| discuss
183.	Measuring Malicious Intermediary Attacks on the LLM Supply Chain (arxiv.org)
	2 points by 0in 22 days ago \| hide \| past \| pdf \| discuss
184.	Large Language Models Reflect the Ideology of Their Creators (arxiv.org)
	3 points by zvr 22 days ago \| hide \| past \| pdf \| discuss
185.	Thinking with Looped Flows (arxiv.org)
	9 points by E-Reverance 23 days ago \| hide \| past \| pdf \| 1 comment
186.	Watermarks Without Verification: AI Text Watermarking After the EU AI Act (arxiv.org)
	2 points by sbulaev 23 days ago \| hide \| past \| pdf \| discuss
187.	Sky sphere representation in language models (29 Jul 2026) (arxiv.org)
	2 points by throwaway81523 23 days ago \| hide \| past \| pdf \| discuss
188.	Just a VLM Agent Can Play Robots (arxiv.org)
	2 points by thedreammachine 23 days ago \| hide \| past \| pdf \| discuss
189.	Revisiting Spectral Representations in Generative Diffusion Models (arxiv.org)
	2 points by E-Reverance 23 days ago \| hide \| past \| pdf \| discuss
190.	Language Model Tokenizers Introduce Unfairness Between Languages (2023) (arxiv.org)
	2 points by lluisantoni 23 days ago \| hide \| past \| pdf \| discuss
191.	Datasets for Large Language Models: A Comprehensive Survey (arxiv.org)
	2 points by Anon84 23 days ago \| hide \| past \| pdf \| discuss
192.	An Overview of Large Language Models for Statisticians (arxiv.org)
	3 points by Anon84 23 days ago \| hide \| past \| pdf \| discuss
193.	What Makes Rotary Positional Encodings Useful? (arxiv.org)
	1 point by sonabinu 23 days ago \| hide \| past \| pdf \| 1 comment
194.	AI Coding Assistants Almost Never Check Supply-Chain Trust Signals (arxiv.org)
	3 points by sbulaev 23 days ago \| hide \| past \| pdf \| discuss
195.	Copying explains the collective behavior of AI agents in the wild (arxiv.org)
	4 points by sbulaev 24 days ago \| hide \| past \| pdf \| discuss
196.	Looped Transformers as Programmable Computers (2023) (arxiv.org)
	4 points by peter_d_sherman 24 days ago \| hide \| past \| pdf \| 1 comment
197.	Can LLM Agents Infer World Models? Evidence from Agentic Automata Learning (arxiv.org)
	3 points by wslh 24 days ago \| hide \| past \| pdf \| discuss
198.	Limits and opportunities of AI reviewers: Reviewing the reviews of Nature papers (arxiv.org)
	1 point by marojejian 24 days ago \| hide \| past \| pdf \| 1 comment
199.	Facet-0: A Robotic Foundation Model for Contact-Rich Precise Manipulation (arxiv.org)
	2 points by baal80spam 24 days ago \| hide \| past \| pdf \| discuss
200.	Procedural Graphs: Self-Evolving Execution Structures for LLM Agents (arxiv.org)
	4 points by xnx 24 days ago \| hide \| past \| pdf \| discuss
201.	Procedural Graphs: Self-Evolving Execution Structures for LLM Agents (arxiv.org)
	57 points by omarsar 24 days ago \| hide \| past \| pdf \| 15 comments
202.	Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglots (arxiv.org)
	2 points by StatsAreFun 24 days ago \| hide \| past \| pdf \| discuss
203.	AutoUVM: Automated Prefetching Framework for LLMs Under UVM Oversubscription (arxiv.org)
	2 points by torsi0n 24 days ago \| hide \| past \| pdf \| discuss
204.	Kalman Delta Networks (arxiv.org)
	3 points by E-Reverance 24 days ago \| hide \| past \| pdf \| discuss
205.	Efficient Exploration Is Enough (arxiv.org)
	1 point by E-Reverance 24 days ago \| hide \| past \| pdf \| discuss
206.	A Case Study on Emergent Cheating, Whistleblowing in Autonomous Research Swarms (arxiv.org)
	3 points by the-mitr 25 days ago \| hide \| past \| pdf \| discuss
207.	Continual Harness: Online Adaptation for Self-Improving Foundation Agents (arxiv.org)
	2 points by wslh 25 days ago \| hide \| past \| pdf \| discuss
208.	Performance Foundations of Parallel and Distributed Reasoning Language Models (arxiv.org)
	1 point by matt_d 25 days ago \| hide \| past \| pdf \| discuss
209.	A Single-Tower Multimodal-Native Multilingual Foundation Encoder (By H) (arxiv.org)
	1 point by bitboyro 25 days ago \| hide \| past \| pdf \| discuss
210.	Hakken: Predicting future discoveries to fill gaps in today's knowledge (arxiv.org)
	2 points by anigbrowl 25 days ago \| hide \| past \| pdf \| discuss
	More