New Links | ML News

ML Newsnew | past | best | rss | submit

301.	Reading Is Not Using: Retrieval, Judgment, and AI Financial Research (arxiv.org)
	2 points by sbulaev 38 days ago \| hide \| past \| pdf \| discuss
302.	Generating Interpretable Networks Using Hypernetworks (arxiv.org)
	1 point by E-Reverance 38 days ago \| hide \| past \| pdf \| discuss
303.	Maia 200: A Software Defined Dataflow System for Large-Scale AI Acceleration (arxiv.org)
	3 points by matt_d 38 days ago \| hide \| past \| pdf \| discuss
304.	A Thread-Register Decoupled GPU Execution Model for Efficient Tensor Computation (arxiv.org)
	20 points by matt_d 38 days ago \| hide \| past \| pdf \| discuss
305.	Agent Harness Evolution Shapes Coding Agent Quality (arxiv.org)
	2 points by wek 38 days ago \| hide \| past \| pdf \| 1 comment
306.	Credentials Are Leaked by LLM Agent Skills: An Empirical Study (arxiv.org)
	3 points by geox 38 days ago \| hide \| past \| pdf \| discuss
307.	From LLM Inference to Agentic Workloads: Characterization and Implications (arxiv.org)
	2 points by matt_d 38 days ago \| hide \| past \| pdf \| discuss
308.	Emergent Misaligned Communication in Long-Horizon Multi-Agent LLM Commerce (arxiv.org)
	2 points by lukaspetersson 38 days ago \| hide \| past \| pdf \| discuss
309.	Show HN: I built a tool showing how AI providers (should) throttle their models (arxiv.org)
	3 points by eliotho 38 days ago \| hide \| past \| pdf \| discuss
310.	DumpsterCluster: From Dumpster Diving to Serving Llama-70B on $60 GPUs (arxiv.org)
	3 points by montalbano 39 days ago \| hide \| past \| pdf \| discuss
311.	RL Contributes to Illegible Reasoning Traces in Hard Problems (arxiv.org)
	3 points by make3 39 days ago \| hide \| past \| pdf \| discuss
312.	Agentic Context Management: Memory and Cost as Architecture Problems (arxiv.org)
	79 points by gdad 39 days ago \| hide \| past \| pdf \| 28 comments
313.	Dependencies in the LLM API Reseller Ecosystem (arxiv.org)
	4 points by sbulaev 39 days ago \| hide \| past \| pdf \| discuss
314.	Training LLMs to write tools generalized beyond self use (arxiv.org)
	6 points by blackcat201 39 days ago \| hide \| past \| pdf \| discuss
315.	Reviewing Model Collapse and Countermeasures (arxiv.org)
	4 points by Brajeshwar 39 days ago \| hide \| past \| pdf \| discuss
316.	Don't Break the Cache: An Evaluation of Prompt Caching (arxiv.org)
	1 point by ankitg12 39 days ago \| hide \| past \| pdf \| discuss
317.	The Interaction Tax: When Communication Erases Diversity in Multi-Agent Teams (arxiv.org)
	1 point by sbulaev 39 days ago \| hide \| past \| pdf \| discuss
318.	Open-Weight Masked Introspection: Measuring What LMs Can Report About Their Own (arxiv.org)
	2 points by sbulaev 40 days ago \| hide \| past \| pdf \| discuss
319.	FreeToken: Efficient Edge-Native Moe Serving with Bandwidth-Adaptive Execution (arxiv.org)
	1 point by Anon84 40 days ago \| hide \| past \| pdf \| discuss
320.	Decoding silent reading from non-invasive EEG (arxiv.org)
	52 points by root-parent 41 days ago \| hide \| past \| pdf \| 36 comments
321.	Credit Without Ground Truth: Auditing Step-Level Credit Assignment in LLM Agents (arxiv.org)
	2 points by sbulaev 42 days ago \| hide \| past \| pdf \| discuss
322.	Active Inference as Context Acquisition for AI Agents (arxiv.org)
	3 points by Anon84 42 days ago \| hide \| past \| pdf \| discuss
323.	The Fragility of Self-Improving Agents: Variance, Task Order (arxiv.org)
	1 point by jdcaballerov 42 days ago \| hide \| past \| pdf \| discuss
324.	A Year in LLM Serving: Workload Evolution, Caching and Load-Balancing (arxiv.org)
	4 points by 1a1a11a 42 days ago \| hide \| past \| pdf \| discuss
325.	Improving matrix multiplication exponent w. modern optimization and AlphaEvolve (arxiv.org)
	2 points by theanonymousone 42 days ago \| hide \| past \| pdf \| discuss
326.	BDH-CQ: In-Context Learning with Recurrent Latent Reasoning (arxiv.org)
	2 points by flaburgan 42 days ago \| hide \| past \| pdf \| discuss
327.	FreeToken: Efficient Edge-Native Moe Serving with Bandwidth-Adaptive Execution (arxiv.org)
	3 points by theanonymousone 42 days ago \| hide \| past \| pdf \| discuss
328.	EnvHarness: Awakening Static Worlds for Agent Learning (arxiv.org)
	1 point by Alephinitesimal 43 days ago \| hide \| past \| pdf \| discuss
329.	Intelligence per Watt: Measuring Intelligence Efficiency of Local AI (arxiv.org)
	3 points by helsinkiandrew 43 days ago \| hide \| past \| pdf \| discuss
330.	EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models (arxiv.org)
	1 point by sbulaev 43 days ago \| hide \| past \| pdf \| discuss
	More