New Links | ML News

ML Newsnew | past | best | rss | submit

481.	Nvidia-Labs OO Agents: Native Python Object-Oriented Agents (arxiv.org)
	2 points by javaeeeee 61 days ago \| hide \| past \| pdf \| 1 comment
482.	Minimum Description Length Meets Singular Learning Theory (arxiv.org)
	2 points by E-Reverance 61 days ago \| hide \| past \| pdf \| discuss
483.	Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents (arxiv.org)
	2 points by zhinit 61 days ago \| hide \| past \| pdf \| discuss
484.	Inducing language models to assert their own consciousness restores human values (arxiv.org)
	3 points by Mizza 62 days ago \| hide \| past \| pdf \| discuss
485.	Language Models Agree with Each Other, Not with Readers (arxiv.org)
	3 points by sbulaev 62 days ago \| hide \| past \| pdf \| discuss
486.	Demystifying Deep Learning Compiler Front End Bugs: An LLM-Aided Empirical Study (arxiv.org)
	1 point by matt_d 62 days ago \| hide \| past \| pdf \| discuss
487.	GPU Accelerated Genetic Programming for Symbolic Regression – Beagle Framework (arxiv.org)
	2 points by bane 62 days ago \| hide \| past \| pdf \| discuss
488.	Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs (arxiv.org)
	1 point by sbulaev 63 days ago \| hide \| past \| pdf \| discuss
489.	IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests (arxiv.org)
	2 points by yruzin 63 days ago \| hide \| past \| pdf \| discuss
490.	Token Reduction Is Not Cost Reduction (arxiv.org)
	3 points by umitkaanusta 63 days ago \| hide \| past \| pdf \| 1 comment
491.	Fidelity Is Not Safety: Compressed LLMs Pass Quality Guards yet Invent (arxiv.org)
	2 points by sbulaev 63 days ago \| hide \| past \| pdf \| discuss
492.	LLMs Can Infer Political Alignment from Online Conversations (arxiv.org)
	1 point by Anon84 63 days ago \| hide \| past \| pdf \| 1 comment
493.	Manta: Network Topology Adaptation for Self-Evolving Multi-Agent Systems (arxiv.org)
	2 points by danbitengo 64 days ago \| hide \| past \| pdf \| discuss
494.	Inducing language models to assert their own consciousness restores human (arxiv.org)
	1 point by sbulaev 64 days ago \| hide \| past \| pdf \| discuss
495.	Explorative Modeling – A new axis for pre-training (arxiv.org)
	11 points by piesauce 64 days ago \| hide \| past \| pdf \| 5 comments
496.	CircuitProver: Agentic Lean 4 Theorem Proving for Hardware Verification (arxiv.org)
	2 points by Jimmc414 64 days ago \| hide \| past \| pdf \| discuss
497.	Metis: Memory Foundation Model (arxiv.org)
	2 points by mfiguiere 64 days ago \| hide \| past \| pdf \| discuss
498.	Orca-Bench: How Ready Are Language Model Agents for Oncall? (arxiv.org)
	30 points by yruzin 64 days ago \| hide \| past \| pdf \| 11 comments
499.	Neuro-Inspired Inverse Learning for Planning and Control (arxiv.org)
	3 points by kensai 64 days ago \| hide \| past \| pdf \| 1 comment
500.	Stealthy Concurrent Audio Prompt Injections Against Multimodal LLM Agents (arxiv.org)
	2 points by zhinit 65 days ago \| hide \| past \| pdf \| discuss
501.	Study: Coding agents rarely retrieve open-source contribution rules (arxiv.org)
	2 points by wek 65 days ago \| hide \| past \| pdf \| discuss
502.	Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling (arxiv.org)
	2 points by sbulaev 65 days ago \| hide \| past \| pdf \| discuss
503.	Specula: Scaling formal specs for autonomous model checking of system code (arxiv.org)
	3 points by matt_d 65 days ago \| hide \| past \| pdf \| discuss
504.	At-the-Roofline Sparse Tensor Contractions on Vector Processors for Inference (arxiv.org)
	1 point by matt_d 65 days ago \| hide \| past \| pdf \| discuss
505.	Can AI agents conduct open-ended AI research? (arxiv.org)
	5 points by randomwalker 65 days ago \| hide \| past \| pdf \| discuss
506.	Towards End-to-End Automation of AI Research [pdf] (arxiv.org)
	3 points by dgellow 65 days ago \| hide \| past \| pdf \| 1 comment
507.	Adversarial Code Obfuscation for Defending Against LLM-Based Analysis (arxiv.org)
	3 points by dirkc 66 days ago \| hide \| past \| pdf \| 1 comment
508.	CliffordNet: All You Need Is Geometric Algebra[ArXiv:2601.06793] (arxiv.org)
	2 points by unprovable 66 days ago \| hide \| past \| pdf \| discuss
509.	Hearsay: Vision-Language Medical Diagnoses Without an Image (arxiv.org)
	2 points by sbulaev 66 days ago \| hide \| past \| pdf \| discuss
510.	Fleet: Hierarchical Task-Based Abstraction for Megakernels on Multi-Die GPUs (arxiv.org)
	2 points by matt_d 66 days ago \| hide \| past \| pdf \| discuss
	More