New Links | ML News

ML Newsnew | past | best | rss | submit

421.	A Watermark for Large Language Models (arxiv.org)
	4 points by matheusmoreira 53 days ago \| hide \| past \| pdf \| discuss
422.	Towards Expert-Level Medical AI for Real-Time Video Consultations (arxiv.org)
	3 points by tcp_handshaker 53 days ago \| hide \| past \| pdf \| discuss
423.	Emergent Introspective Awareness in Large Language Models (arxiv.org)
	72 points by doener 53 days ago \| hide \| past \| pdf \| 33 comments
424.	Previous-Token Prediction Based LLM Near-Exact Prompt Reconstruction (arxiv.org)
	2 points by doener 53 days ago \| hide \| past \| pdf \| discuss
425.	Stealing Reasoning Traces from Proprietary LLM APIs (arxiv.org)
	9 points by samvher 53 days ago \| hide \| past \| pdf \| discuss
426.	ArchAgent v2: A Case Study with the Data Prefetching Championship (arxiv.org)
	3 points by root-parent 54 days ago \| hide \| past \| pdf \| discuss
427.	Stealing Reasoning Traces from Proprietary LLM APIs (arxiv.org)
	5 points by sbulaev 54 days ago \| hide \| past \| pdf \| discuss
428.	Ouroboros: A coding agent that evolves its own harness and tops agent benchmarks (arxiv.org)
	5 points by ndreeew 54 days ago \| hide \| past \| pdf \| 1 comment
429.	Attention-Only Transformers (arxiv.org)
	3 points by MediaSquirrel 54 days ago \| hide \| past \| pdf \| 1 comment
430.	A Watermark for Large Language Models (arxiv.org)
	3 points by m-chrzan 54 days ago \| hide \| past \| pdf \| discuss
431.	EvoHarnessRL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents (arxiv.org)
	3 points by matt_d 54 days ago \| hide \| past \| pdf \| discuss
432.	Mind the Gaps: Mixture-of-Minds for Human Simulation (arxiv.org)
	2 points by jtewright 54 days ago \| hide \| past \| pdf \| 1 comment
433.	HLSmith: An Expert-Guided Agentic Framework for C/C++-to-HLS Translation (arxiv.org)
	2 points by rbanffy 54 days ago \| hide \| past \| pdf \| discuss
434.	Composer 2 Technical Report (arxiv.org)
	1 point by ronfriedhaber 55 days ago \| hide \| past \| pdf \| discuss
435.	Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits (arxiv.org)
	2 points by sbulaev 55 days ago \| hide \| past \| pdf \| discuss
436.	HCCL: Collective Communication for Meta Training and Inference Accelerators (arxiv.org)
	1 point by matt_d 55 days ago \| hide \| past \| pdf \| discuss
437.	MatrAIx: Simulating the World with 8.3B Persona Agents (arxiv.org)
	4 points by birriel 55 days ago \| hide \| past \| pdf \| 2 comments
438.	LLMs Get Lost in Evolving User Intent (arxiv.org)
	2 points by Anon84 55 days ago \| hide \| past \| pdf \| discuss
439.	ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence (arxiv.org)
	2 points by simonpure 55 days ago \| hide \| past \| pdf \| discuss
440.	Answer First, Reason Later: Commitment Order in Diffusion LLMs (arxiv.org)
	3 points by sbulaev 56 days ago \| hide \| past \| pdf \| discuss
441.	Benchmarking LLMs on File System Design and Implementation (arxiv.org)
	4 points by matt_d 56 days ago \| hide \| past \| pdf \| discuss
442.	Towards a Risk Assessment of Malicious Skill Files in Coding Agents (arxiv.org)
	1 point by sbulaev 57 days ago \| hide \| past \| pdf \| discuss
443.	Robust AI Security and Alignment: A Sisyphean Endeavor? (arxiv.org)
	3 points by joshcsimmons 57 days ago \| hide \| past \| pdf \| discuss
444.	TensorLift: Auto Extraction of ISA Semantics from Accelerator RTL via MLIR (arxiv.org)
	1 point by matt_d 57 days ago \| hide \| past \| pdf \| discuss
445.	HarnessOpt-Bench: Evaluating LLMs at Harness Optimization (arxiv.org)
	3 points by wslh 57 days ago \| hide \| past \| pdf \| discuss
446.	AI Meet CAD: Beat Opus/Mythos 5, GPT 5.6 Sol on BenchCAD (arxiv.org)
	2 points by SUPERustam 58 days ago \| hide \| past \| pdf \| 1 comment
447.	The Illusion of Visual Tool-Use: A Causal Audit of Thinking with Images (arxiv.org)
	1 point by sbulaev 58 days ago \| hide \| past \| pdf \| discuss
448.	INT2 KV-cache quantization is getting surprisingly good (arxiv.org)
	3 points by yunuyean 58 days ago \| hide \| past \| pdf \| discuss
449.	SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems (arxiv.org)
	1 point by sbulaev 58 days ago \| hide \| past \| pdf \| discuss
450.	Benchmarking the Residual: What Long-Horizon Evals Add Beyond Short-Task Perf (arxiv.org)
	1 point by matt_d 58 days ago \| hide \| past \| pdf \| discuss
	More