New Links | ML News

ML Newsnew | past | best | rss | submit

1141.	Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens (2025) (arxiv.org)
	1 point by SomaticPirate 163 days ago \| hide \| past \| pdf \| 1 comment
1142.	Different language models learn similar number representations (arxiv.org)
	115 points by Anon84 163 days ago \| hide \| past \| pdf \| 47 comments
1143.	Can LLMs recapitulate Americans' responses to public opinion polling questions? (arxiv.org)
	1 point by PaulHoule 163 days ago \| hide \| past \| pdf \| discuss
1144.	Agyn: A Multi-Agent System for Team-Based Autonomous Software Engineering (arxiv.org)
	2 points by wek 164 days ago \| hide \| past \| pdf \| discuss
1145.	Sophia: A Scalable Second-Order Optimizer for Language Model Pre-Training (arxiv.org)
	4 points by Anon84 164 days ago \| hide \| past \| pdf \| 1 comment
1146.	The Broader Landscape of Robustness in Algorithmic Statistics (arxiv.org)
	1 point by sebg 164 days ago \| hide \| past \| pdf \| discuss
1147.	Image Generators Are Generalist Vision Learners (arxiv.org)
	2 points by mohsen1 164 days ago \| hide \| past \| pdf \| discuss
1148.	SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving (arxiv.org)
	2 points by matt_d 165 days ago \| hide \| past \| pdf \| discuss
1149.	Qwen3.5-Omni Technical Report (arxiv.org)
	7 points by gmays 165 days ago \| hide \| past \| pdf \| discuss
1150.	Scaling Test-Time Compute for Agentic Coding (arxiv.org)
	2 points by matt_d 165 days ago \| hide \| past \| pdf \| discuss
1151.	Benchmarking Cloud vs. Local LLMs Why back end choice matters more than quant (arxiv.org)
	2 points by tleitch 166 days ago \| hide \| past \| pdf \| discuss
1152.	FPGA-based tiled matrix multiplication accelerator for self-attention (arxiv.org)
	3 points by sha_rad 166 days ago \| hide \| past \| pdf \| discuss
1153.	Lookalike3D: Seeing Double in 3D (arxiv.org)
	1 point by PaulHoule 166 days ago \| hide \| past \| pdf \| discuss
1154.	Faster LLM Inference via Sequential Monte Carlo (arxiv.org)
	3 points by matt_d 166 days ago \| hide \| past \| pdf \| discuss
1155.	A foundation model for electrodermal activity data (arxiv.org)
	2 points by PaulHoule 166 days ago \| hide \| past \| pdf \| discuss
1156.	Do Large Language Models Know Which Published Articles Have Been Retracted? (arxiv.org)
	4 points by Brajeshwar 166 days ago \| hide \| past \| pdf \| discuss
1157.	Hierarchical Planning with Latent World Models (arxiv.org)
	2 points by fofoz 166 days ago \| hide \| past \| pdf \| discuss
1158.	KV Cache Compression 900000x Beyond TurboQuant and Per-Vector Shannon Limit (arxiv.org)
	46 points by EGreg 167 days ago \| hide \| past \| pdf \| 42 comments
1159.	Stable End-to-End Joint-Embedding Predictive Architecture from Pixels (arxiv.org)
	5 points by wslh 167 days ago \| hide \| past \| pdf \| discuss
1160.	ASI-Evolve: AI Accelerates AI (arxiv.org)
	1 point by Mars008 167 days ago \| hide \| past \| pdf \| discuss
1161.	Agentic Context Engineering:Evolving Contexts for Self-Improving Language Models (arxiv.org)
	2 points by matt_d 167 days ago \| hide \| past \| pdf \| discuss
1162.	Neuro-Symbolic Ode Discovery with Latent Grammar Flow (arxiv.org)
	1 point by ahsillyme 167 days ago \| hide \| past \| pdf \| discuss
1163.	SoK: Security of Autonomous LLM Agents in Agentic Commerce (arxiv.org)
	3 points by omer_k 168 days ago \| hide \| past \| pdf \| discuss
1164.	Mixture-of-Depths Attention (arxiv.org)
	4 points by neehao 168 days ago \| hide \| past \| pdf \| 1 comment
1165.	Tide: Token-Informed Depth Execution for Per-Token Early Exit in LLM Inference (arxiv.org)
	3 points by OsamaJaber 168 days ago \| hide \| past \| pdf \| 1 comment
1166.	Prefill-as-a-Service:KVCache of Next-Generation Models Could Go Cross-Datacenter (arxiv.org)
	44 points by matt_d 169 days ago \| hide \| past \| pdf \| 1 comment
1167.	Generative artificial intelligence for computational chemistry (arxiv.org)
	3 points by bdg 169 days ago \| hide \| past \| pdf \| discuss
1168.	LLMs Exhibit Significantly Lower Uncertainty in Creative Writing Than Writers (arxiv.org)
	1 point by wslh 169 days ago \| hide \| past \| pdf \| discuss
1169.	The Newton–Muon Optimizer (arxiv.org)
	1 point by sonabinu 169 days ago \| hide \| past \| pdf \| discuss
1170.	Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems (arxiv.org)
	3 points by Anon84 169 days ago \| hide \| past \| pdf \| discuss
	More