New Links | ML News

ML Newsnew | past | best | rss | submit

2101.	Chain-of-Thought Hijacking (arxiv.org)
	2 points by belter 339 days ago \| hide \| past \| pdf \| discuss
2102.	Investigating How Prompt Politeness Affects LLM Accuracy (arxiv.org)
	4 points by awb 339 days ago \| hide \| past \| pdf \| 2 comments
2103.	Emu3.5: Native Multimodal Models Are World Learners (arxiv.org)
	3 points by progbits 339 days ago \| hide \| past \| pdf \| 1 comment
2104.	Reasoning models reason well, until they don't (arxiv.org)
	218 points by optimalsolver 340 days ago \| hide \| past \| pdf \| 217 comments
2105.	Collective Communication for 100k+ GPUs (arxiv.org)
	1 point by charleshn 340 days ago \| hide \| past \| pdf \| discuss
2106.	Multi-Domain Rubrics Requiring Professional Knowledge to Answer and Judge (arxiv.org)
	2 points by PaulHoule 340 days ago \| hide \| past \| pdf \| discuss
2107.	Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity (arxiv.org)
	2 points by CharlesW 340 days ago \| hide \| past \| pdf \| discuss
2108.	Predictability Enables Parallelization (arxiv.org)
	2 points by leokoz8 340 days ago \| hide \| past \| pdf \| discuss
2109.	Language models are injective and hence invertible (arxiv.org)
	231 points by mazsa 341 days ago \| hide \| past \| pdf \| 147 comments
2110.	Drug Discovery with Apex Protocol by Nvidia and Numerion Labs (arxiv.org)
	2 points by nkko 341 days ago \| hide \| past \| pdf \| discuss
2111.	Benchmarking World-Model Learning (arxiv.org)
	2 points by mpweiher 341 days ago \| hide \| past \| pdf \| discuss
2112.	Rectifying Shortcut Behaviors in Preference-Based Reward Learning (arxiv.org)
	1 point by PaulHoule 341 days ago \| hide \| past \| pdf \| discuss
2113.	Language Models Are Injective and Hence Invertible (arxiv.org)
	1 point by moondistance 341 days ago \| hide \| past \| pdf \| 2 comments
2114.	Fast frequency reconstruction using DL for event recognition in ring laser data (arxiv.org)
	2 points by PaulHoule 341 days ago \| hide \| past \| pdf \| discuss
2115.	Apple: Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing (arxiv.org)
	6 points by 7777777phil 341 days ago \| hide \| past \| pdf \| discuss
2116.	An efficient probabilistic hardware architecture for diffusion-like models (arxiv.org)
	3 points by iamronaldo 341 days ago \| hide \| past \| pdf \| discuss
2117.	Generating Creative Chess Puzzles (arxiv.org)
	3 points by FergusArgyll 341 days ago \| hide \| past \| pdf \| 1 comment
2118.	Improving Topic Modeling of Social Media Short Texts with Rephrasing (arxiv.org)
	2 points by PaulHoule 341 days ago \| hide \| past \| pdf \| discuss
2119.	DeepSeek-OCR: Contexts Optical Compression (arxiv.org)
	2 points by yubblegum 341 days ago \| hide \| past \| pdf \| discuss
2120.	Language Models Are Injective and Hence Invertible (arxiv.org)
	4 points by mococa 341 days ago \| hide \| past \| pdf \| 1 comment
2121.	Reasoning with Sampling: Your Base Model Is Smarter Than You Think (arxiv.org)
	2 points by jonbaer 341 days ago \| hide \| past \| pdf \| discuss
2122.	Language Models Are Injective and Hence Invertible (arxiv.org)
	1 point by qsort 342 days ago \| hide \| past \| pdf \| discuss
2123.	Why Foundation Models in Pathology Are Failing (arxiv.org)
	4 points by 50kIters 342 days ago \| hide \| past \| pdf \| 1 comment
2124.	The Principles of Diffusion Models (arxiv.org)
	10 points by dvrp 342 days ago \| hide \| past \| pdf \| 1 comment
2125.	Semantic Compression with Large Language Models (arxiv.org)
	2 points by manikandaraj 342 days ago \| hide \| past \| pdf \| 1 comment
2126.	One ruler to measure them all: Benchmarking multilingual long-context LLMs (arxiv.org)
	2 points by danielam 342 days ago \| hide \| past \| pdf \| discuss
2127.	Huxley-Gödel Machine (arxiv.org)
	2 points by jadelcastillo 342 days ago \| hide \| past \| pdf \| 1 comment
2128.	LLMs can hide text in other text of the same length (arxiv.org)
	2 points by goplayoutside 342 days ago \| hide \| past \| pdf \| 1 comment
2129.	Learning from Abundant User Dissatisfaction in Real-World Preference Learning (arxiv.org)
	3 points by PaulHoule 343 days ago \| hide \| past \| pdf \| discuss
2130.	Language Models Are Injective and Hence Invertible (arxiv.org)
	1 point by porridgeraisin 343 days ago \| hide \| past \| pdf \| discuss
	More