ML Newsnew | past | best | rss | submit about
571. Time-Frequency Consistency Learning for Robust Speech Deepfake Detection (arxiv.org)
4 points by zhinit 74 days ago | hide | past | pdf | discuss
572. Show HN: The First Open Source Diffusion ASR Audio Model 15x Faster Than Whisper (arxiv.org)
4 points by khurdula 75 days ago | hide | past | pdf | discuss
573. Loop the Loopies (arxiv.org)
2 points by Anon84 75 days ago | hide | past | pdf | discuss
574. Sobek: Streaming Equivariant Tensor Product Convolutions (arxiv.org)
1 point by sbulaev 75 days ago | hide | past | pdf | discuss
575. Open Meditron: An Auditable Pipeline for Clinical LLMs (arxiv.org)
1 point by instagraham 75 days ago | hide | past | pdf | discuss
576. Malicious Agent Skills in the Wild (arxiv.org)
2 points by yruzin 75 days ago | hide | past | pdf | discuss
577. Kimi Linear: An Expressive, Efficient Attention Architecture (arxiv.org)
3 points by ashish01 75 days ago | hide | past | pdf | discuss
578. Every Microsecond Matters:Achieving Near SpeedOfLight Latency in GPU Collectives (arxiv.org)
2 points by matt_d 75 days ago | hide | past | pdf | discuss
579. Down with the Hierarchy: The "H" in HNSW Stands for "Hubs" (arxiv.org)
2 points by paldepind2 76 days ago | hide | past | pdf | discuss
580. AgentAbstain: Do LLM Agents Know When Not to Act? (arxiv.org)
3 points by embedding-shape 76 days ago | hide | past | pdf | discuss
581. Coercion and Deception in AI-to-AI Management: An Agentic Benchmark (arxiv.org)
1 point by sbulaev 76 days ago | hide | past | pdf | discuss
582. AI Watermark Evidence Fails Forensic Readiness: An Empirical Evaluation (arxiv.org)
1 point by sbulaev 76 days ago | hide | past | pdf | discuss
583. The Cost and Network Limits of Space-Based AI Compute (arxiv.org)
3 points by Jimmc414 76 days ago | hide | past | pdf | discuss
584. Don't Predict, Prioritize: Rethinking GPU Reliability Assessment (arxiv.org)
1 point by Jimmc414 76 days ago | hide | past | pdf | discuss
585. Do Language Models Plan Ahead for Future Tokens? (2024) (arxiv.org)
2 points by Alifatisk 77 days ago | hide | past | pdf | discuss
586. Petals: Collaborative Inference and Fine-Tuning of Large Models (arxiv.org)
2 points by rglover 77 days ago | hide | past | pdf | discuss
587. Reading Between the Dots: Decoding Hidden Computation Across Filler Tokens (arxiv.org)
2 points by user_7832 77 days ago | hide | past | pdf | 2 comments
588. One token is enough: fingerprinting LLMs from one token output distributions (arxiv.org)
6 points by anigbrowl 77 days ago | hide | past | pdf | discuss
589. Multi-Agent LLMs Fail to Explore Each Other (arxiv.org)
3 points by Anon84 77 days ago | hide | past | pdf | 1 comment
590. Reading Between the Dots: Decoding Hidden Computation Across Filler Tokens (arxiv.org)
1 point by kristianp 77 days ago | hide | past | pdf | discuss
591. Reading Between the Dots: Decoding Hidden Computation Across Filler Tokens (arxiv.org)
1 point by Luc 78 days ago | hide | past | pdf | discuss
592. Reading Between Dots: Decoding Hidden Computation Across Filler Tokens (ICML'26) (arxiv.org)
1 point by vismit2000 78 days ago | hide | past | pdf | discuss
593. Agent Security Is a Systems Problem (arxiv.org)
10 points by bradreaves2 78 days ago | hide | past | pdf | 2 comments
594. LLM-as-a-Verifier: A General-Purpose Verification Framework (arxiv.org)
2 points by tie-in 79 days ago | hide | past | pdf | discuss
595. Real Money, Fake Models: Deceptive Model Claims in Shadow APIs (arxiv.org)
1 point by sysoleg 79 days ago | hide | past | pdf | discuss
596. LLM Evaluators are Biased across Languages (arxiv.org)
2 points by sbulaev 79 days ago | hide | past | pdf | 1 comment
597. Show HN: KV-Cache Grafting – Boosting frozen 12B LLMs to 93.3% AIME accuracy (arxiv.org)
3 points by Corbenic 79 days ago | hide | past | pdf | discuss
598. Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning (arxiv.org)
62 points by binyu 79 days ago | hide | past | pdf | 27 comments
599. Your AI agent doesn't know when its memory is gone (arxiv.org)
3 points by venkateshamatam 79 days ago | hide | past | pdf | discuss
600. Mathematics of Data Science (arxiv.org)
222 points by Anon84 79 days ago | hide | past | pdf | 14 comments
About | RSS | RSS (all) | HN arXiv