New Links | ML News

ML Newsnew | past | best | rss | submit

1861.	Let's (Not) Just Put Things in Context: Test-Time Training for Long-Context LLMs (arxiv.org)
	1 point by elashri 292 days ago \| hide \| past \| pdf \| discuss
1862.	Apriel-H1: Towards Efficient Enterprise Reasoning Models (arxiv.org)
	1 point by guiriduro 292 days ago \| hide \| past \| pdf \| 1 comment
1863.	Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs (arxiv.org)
	7 points by bediger4000 292 days ago \| hide \| past \| pdf \| 1 comment
1864.	Beaver: An Efficient Deterministic LLM Verifier (arxiv.org)
	1 point by tshanmu 293 days ago \| hide \| past \| pdf \| 1 comment
1865.	The Debugging Decay Index: Rethinking Debugging Strategies for Code LLMs (arxiv.org)
	2 points by chengchang316 293 days ago \| hide \| past \| pdf \| 2 comments
1866.	Detailed balance in large language model-driven agents (arxiv.org)
	48 points by Anon84 293 days ago \| hide \| past \| pdf \| 5 comments
1867.	Large language models are not about natural language (arxiv.org)
	2 points by 50kIters 293 days ago \| hide \| past \| pdf \| discuss
1868.	Audio Frequency-Time Dual Domain Evaluation on Depression Diagnosis (arxiv.org)
	2 points by internetguy 294 days ago \| hide \| past \| pdf \| discuss
1869.	Detailed balance in large language model-driven agents (arxiv.org)
	1 point by gmays 294 days ago \| hide \| past \| pdf \| discuss
1870.	Gradient Descent Algorithm Survey (arxiv.org)
	3 points by PaulHoule 294 days ago \| hide \| past \| pdf \| 1 comment
1871.	Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in LLMs (arxiv.org)
	3 points by trueduke 294 days ago \| hide \| past \| pdf \| discuss
1872.	AI Agents vs. Pentesters (arxiv.org)
	2 points by takira 295 days ago \| hide \| past \| pdf \| discuss
1873.	Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs (arxiv.org)
	3 points by _tk_ 295 days ago \| hide \| past \| pdf \| discuss
1874.	An open-source energy and latency profiler for LLMs: ELANA (arxiv.org)
	1 point by nkko 295 days ago \| hide \| past \| pdf \| discuss
1875.	Stronger Normalization-Free Transformers (arxiv.org)
	4 points by mfiguiere 296 days ago \| hide \| past \| pdf \| discuss
1876.	Reproducibility Test-Time Training on Nearest Neighbors for LLMs (arxiv.org)
	2 points by PaulHoule 296 days ago \| hide \| past \| pdf \| discuss
1877.	Reasoning with Sampling: Your Base Model Is Smarter Than You Think (arxiv.org)
	2 points by gmays 296 days ago \| hide \| past \| pdf \| discuss
1878.	AI based hacking compared to humans (arxiv.org)
	2 points by mriguy 297 days ago \| hide \| past \| pdf \| discuss
1879.	Framework for Preventing Unauthorized Zero-Shot Image-to-Image Generation (arxiv.org)
	2 points by PaulHoule 297 days ago \| hide \| past \| pdf \| discuss
1880.	Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers (arxiv.org)
	2 points by andy12_ 297 days ago \| hide \| past \| pdf \| 1 comment
1881.	Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs (arxiv.org)
	2 points by yorwba 297 days ago \| hide \| past \| pdf \| discuss
1882.	Training LLMs for honesty via confessions (arxiv.org)
	70 points by arabello 297 days ago \| hide \| past \| pdf \| 58 comments
1883.	How Well Do LLMs Understand Tunisian Arabic? (arxiv.org)
	3 points by PaulHoule 298 days ago \| hide \| past \| pdf \| discuss
1884.	Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs (arxiv.org)
	7 points by joegibbs 298 days ago \| hide \| past \| pdf \| 2 comments
1885.	How far are we from scaling up next-pixel prediction for image pretraining? (arxiv.org)
	2 points by PaulHoule 298 days ago \| hide \| past \| pdf \| discuss
1886.	Towards a Science of Scaling Agent Systems (arxiv.org)
	2 points by gmays 298 days ago \| hide \| past \| pdf \| discuss
1887.	Streaming Speech Synthesis Without the Trade-Offs: Meet StreamFlow (arxiv.org)
	3 points by PranayBatta 298 days ago \| hide \| past \| pdf \| 1 comment
1888.	Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs (arxiv.org)
	1 point by bearseascape 298 days ago \| hide \| past \| pdf \| discuss
1889.	Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment (arxiv.org)
	2 points by badmonster 299 days ago \| hide \| past \| pdf \| discuss
1890.	Systemization of Knowledge: Security and Safety Challenges in MCP (arxiv.org)
	3 points by sambhu 299 days ago \| hide \| past \| pdf \| discuss
	More