New Links | ML News

ML Newsnew | past | best | rss | submit

781.	DreamX-World 1.0: A General-Purpose Interactive World Model (arxiv.org)
	3 points by berlianta 110 days ago \| hide \| past \| pdf \| discuss
782.	VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small LLMs (arxiv.org)
	6 points by Anon84 110 days ago \| hide \| past \| pdf \| discuss
783.	Brick: SOTA LLM Routing (arxiv.org)
	3 points by FrancescoMassa 110 days ago \| hide \| past \| pdf \| discuss
784.	Greed Is Learned: Visible Incentives as Reward-Hacking Triggers (arxiv.org)
	4 points by Timofeibu 110 days ago \| hide \| past \| pdf \| discuss
785.	Correlated LLM Name Priors and Their Haunting of the Web and Academic Publishing (arxiv.org)
	5 points by wise_blood 110 days ago \| hide \| past \| pdf \| discuss
786.	Cross-Modal Representation Alignment for Time-to-Event Modeling (arxiv.org)
	2 points by ilreb 110 days ago \| hide \| past \| pdf \| discuss
787.	DPBench: Structural Determinants of Multi-Agent LLM Coordination (arxiv.org)
	2 points by najmul-hasan 111 days ago \| hide \| past \| pdf \| discuss
788.	AI language models have favorite names, and we mapped them (arxiv.org)
	4 points by mbrzozowski 111 days ago \| hide \| past \| pdf \| 2 comments
789.	Aegis: A Backup Reflex for Physical AI (arxiv.org)
	2 points by josefchen 111 days ago \| hide \| past \| pdf \| discuss
790.	Deep-Research Agents Can Be Poisoned via User-Generated Content (arxiv.org)
	3 points by rinnetensei 111 days ago \| hide \| past \| pdf \| discuss
791.	You Can Game AI Peer Review with Presentation-Only Revisions (arxiv.org)
	3 points by ilreb 111 days ago \| hide \| past \| pdf \| discuss
792.	Still: Amortized KV Cache Compaction in a Single Forward Pass (arxiv.org)
	3 points by simonpure 112 days ago \| hide \| past \| pdf \| discuss
793.	Brains And LLMs Converge On A Shared Conceptual Space Across Different Languages (arxiv.org)
	5 points by optimalsolver 112 days ago \| hide \| past \| pdf \| discuss
794.	Can AI Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows? (arxiv.org)
	2 points by horticulturist 112 days ago \| hide \| past \| pdf \| discuss
795.	Eywa: Local-first memory for AI agents, with a receipt for every fact (arxiv.org)
	2 points by agentseal 113 days ago \| hide \| past \| pdf \| discuss
796.	PhantomBench: Benchmarking the Non-Existential Threat of Language Models (arxiv.org)
	2 points by root-parent 113 days ago \| hide \| past \| pdf \| 1 comment
797.	HalluHard: A Hard Multi-Turn Hallucination Benchmark (arxiv.org)
	2 points by root-parent 113 days ago \| hide \| past \| pdf \| discuss
798.	UnpredictaBench: A Benchmark for Evaluating Distributional Randomness in LLMs (arxiv.org)
	2 points by matt_d 113 days ago \| hide \| past \| pdf \| discuss
799.	Agentifying Agent Assessment for Openness, Standardization, and Reproducibility (arxiv.org)
	2 points by tcp_handshaker 113 days ago \| hide \| past \| pdf \| discuss
800.	LLMs use recurring ghost authors and personalities (arxiv.org)
	5 points by Gaishan 114 days ago \| hide \| past \| pdf \| discuss
801.	Can I Buy Your KV Cache? (arxiv.org)
	36 points by MediaSquirrel 114 days ago \| hide \| past \| pdf \| 28 comments
802.	Reasoning as Pattern Matching: Shared Mechanisms in Human and LLM Reasoning (arxiv.org)
	1 point by MediaSquirrel 114 days ago \| hide \| past \| pdf \| discuss
803.	Mega Kernels, Written by Agents (arxiv.org)
	2 points by OsamaJaber 114 days ago \| hide \| past \| pdf \| discuss
804.	From Local to Global: A Graph RAG Approach to Query-Focused Summarization (arxiv.org)
	2 points by Anon84 114 days ago \| hide \| past \| pdf \| discuss
805.	Demystifying Hidden-State Recurrence (arxiv.org)
	2 points by ilreb 114 days ago \| hide \| past \| pdf \| discuss
806.	Maxproof (arxiv.org)
	137 points by ilreb 114 days ago \| hide \| past \| pdf \| 13 comments
807.	Doc-to-Atom: Learning to Compile and Compose Memory Atoms (arxiv.org)
	3 points by berlianta 114 days ago \| hide \| past \| pdf \| discuss
808.	Agents' Last Exam (arxiv.org)
	2 points by matt_d 115 days ago \| hide \| past \| pdf \| discuss
809.	Demystifying NVSHMEM: System-Level: Symmetric Memory, Device-Initiated Ops (arxiv.org)
	1 point by matt_d 115 days ago \| hide \| past \| pdf \| discuss
810.	Superficial Beliefs in LLM Decision-Making (arxiv.org)
	3 points by MediaSquirrel 115 days ago \| hide \| past \| pdf \| discuss
	More