New Links | ML News

ML Newsnew | past | best | rss | submit

1441.	Recontextualizing Famous Quotes for Brand Slogan Generation (arxiv.org)
	1 point by PaulHoule 219 days ago \| hide \| past \| pdf \| discuss
1442.	`Lord of the Flies' tribalism emerges among smart AI-Agents (arxiv.org)
	5 points by bikenaga 219 days ago \| hide \| past \| pdf \| 1 comment
1443.	DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference (arxiv.org)
	3 points by gmays 219 days ago \| hide \| past \| pdf \| discuss
1444.	Data Engineering for Scaling LLM Terminal Capabilities (arxiv.org)
	2 points by gmays 220 days ago \| hide \| past \| pdf \| discuss
1445.	The Design Space of Tri-Modal Masked Diffusion Models (arxiv.org)
	1 point by gok 220 days ago \| hide \| past \| pdf \| discuss
1446.	Batch Normalization: Accelerating Deep Network Training (2015) (arxiv.org)
	1 point by doener 220 days ago \| hide \| past \| pdf \| discuss
1447.	Are Emergent Abilities of Large Language Models a Mirage? (2023) (arxiv.org)
	1 point by doener 220 days ago \| hide \| past \| pdf \| discuss
1448.	Emergent Abilities of Large Language Models (2022) (arxiv.org)
	1 point by doener 220 days ago \| hide \| past \| pdf \| discuss
1449.	K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model (arxiv.org)
	2 points by matt_d 220 days ago \| hide \| past \| pdf \| 1 comment
1450.	Midtraining Bridges Pretraining and Posttraining Distributions (arxiv.org)
	1 point by matt_d 220 days ago \| hide \| past \| pdf \| discuss
1451.	Evaluating Memory Structure in LLM Agents (arxiv.org)
	2 points by PaulHoule 220 days ago \| hide \| past \| pdf \| discuss
1452.	Prompt Repetition Improves Non-Reasoning LLMs (arxiv.org)
	1 point by ajoy 220 days ago \| hide \| past \| pdf \| 1 comment
1453.	Ontology-Guided LLMs: Grounding Inference with OpenMath Knowledge (arxiv.org)
	1 point by rkovashikawa 220 days ago \| hide \| past \| pdf \| discuss
1454.	AI buying agents concentrate demand on 2-3 products and ignore the rest (arxiv.org)
	2 points by dmpyatyi 221 days ago \| hide \| past \| pdf \| 1 comment
1455.	Randomness Becomes an Attack Vector in Machine Learning (arxiv.org)
	1 point by PaulHoule 221 days ago \| hide \| past \| pdf \| discuss
1456.	DeepSeek Paper – DualPath: Breaking the Bandwidth Bottleneck in LLM Inference (arxiv.org)
	2 points by dworks 221 days ago \| hide \| past \| pdf \| 1 comment
1457.	Discovering Multiagent Learning Algorithms with Large Language Models (arxiv.org)
	2 points by gmays 221 days ago \| hide \| past \| pdf \| discuss
1458.	Can Chain-of-Thought Reasoning Solve Any Computable Task? (arxiv.org)
	4 points by ryancoleman 221 days ago \| hide \| past \| pdf \| 1 comment
1459.	Hexagon-MLIR: An AI Compilation Stack for Qualcomm's NPUs (arxiv.org)
	3 points by matt_d 221 days ago \| hide \| past \| pdf \| 1 comment
1460.	The Appeal and Reality of Recycling LoRAs with Adaptive Merging (arxiv.org)
	14 points by PaulHoule 221 days ago \| hide \| past \| pdf \| 1 comment
1461.	Aletheia Tackles FirstProof Autonomously (arxiv.org)
	5 points by in-silico 221 days ago \| hide \| past \| pdf \| discuss
1462.	Analyzing Latency Hiding and Parallelism in an MLIR-Based AI Kernel Compiler (arxiv.org)
	1 point by matt_d 221 days ago \| hide \| past \| pdf \| discuss
1463.	Deep Learning: Our Year 1990-1991 (arxiv.org)
	1 point by tosh 222 days ago \| hide \| past \| pdf \| discuss
1464.	Large-scale online deanonymization with LLMs (arxiv.org)
	78 points by mellosouls 222 days ago \| hide \| past \| pdf \| 2 comments
1465.	Frontier Models Exhibit Sophisticated Reasoning in Simulated Nuclear Crises (arxiv.org)
	5 points by consumer451 222 days ago \| hide \| past \| pdf \| discuss
1466.	Large Language Diffusion Models (arxiv.org)
	2 points by andsoitis 222 days ago \| hide \| past \| pdf \| discuss
1467.	Discovering Multiagent Learning Algorithms with Large Language Models (arxiv.org)
	2 points by energy123 222 days ago \| hide \| past \| pdf \| discuss
1468.	Current Large Audio Language Models largely transcribe rather than listen (arxiv.org)
	4 points by earcar 222 days ago \| hide \| past \| pdf \| discuss
1469.	Agents of Chaos (arxiv.org)
	3 points by nextos 222 days ago \| hide \| past \| pdf \| discuss
1470.	AST-Guided Translation of Natural Language into First-Order Logic with LLMs (arxiv.org)
	2 points by PaulHoule 222 days ago \| hide \| past \| pdf \| discuss
	More