New Links | ML News

ML Newsnew | past | best | rss | submit

2161.	Parse: LLM Driven Schema Optimization for Reliable Entity Extraction (arxiv.org)
	2 points by PaulHoule 347 days ago \| hide \| past \| pdf \| discuss
2162.	Antislop: A framework for eliminating repetitive patterns in language models (arxiv.org)
	120 points by Der_Einzige 347 days ago \| hide \| past \| pdf \| 110 comments
2163.	Enhancing Transformer-Based Rerankers with Synthetic Data and LLM Supervision (arxiv.org)
	1 point by PaulHoule 347 days ago \| hide \| past \| pdf \| discuss
2164.	CausalRAG: Integrating Causal Graphs into RAG (arxiv.org)
	2 points by page_index 348 days ago \| hide \| past \| pdf \| 1 comment
2165.	OpenEstimate Evaluating LLMs on Reasoning Under Uncertainty with Real-World Data (arxiv.org)
	1 point by matt_d 348 days ago \| hide \| past \| pdf \| discuss
2166.	The Free Transformer (arxiv.org)
	6 points by aaraujo002 348 days ago \| hide \| past \| pdf \| discuss
2167.	A Novel Spinor-Based Embedding Model for Transformers (arxiv.org)
	4 points by haxiomic 348 days ago \| hide \| past \| pdf \| discuss
2168.	Poisoning Attacks on LLMs Require a Near-Constant Number of Poison Samples (arxiv.org)
	2 points by ievans 348 days ago \| hide \| past \| pdf \| discuss
2169.	Can We Trust Functionally Correct Patches Generated by Code Agents? (arxiv.org)
	1 point by bikenaga 348 days ago \| hide \| past \| pdf \| discuss
2170.	Scaling Reinforcement Learning for Trillion-Scale Thinking Model (arxiv.org)
	4 points by omarsar 348 days ago \| hide \| past \| pdf \| discuss
2171.	The Dragon Hatchling: The missing link between the transformer and brain models (arxiv.org)
	134 points by thatxliner 348 days ago \| hide \| past \| pdf \| 99 comments
2172.	Grasp Any Region: Precise, Contextual Pixel Understanding for Multimodal LLMs (arxiv.org)
	1 point by badmonster 349 days ago \| hide \| past \| pdf \| discuss
2173.	A tiny spectral PMF estimator for large discrete supports (arxiv.org)
	2 points by alexshtf 349 days ago \| hide \| past \| pdf \| discuss
2174.	Query Decomposition for RAG (arxiv.org)
	1 point by salkahfi 349 days ago \| hide \| past \| pdf \| discuss
2175.	Thinking Sparks: Emergent Attention Heads in Reasoning Models (arxiv.org)
	1 point by diwank 349 days ago \| hide \| past \| pdf \| discuss
2176.	Large Language Models Inference Engines Based on Spiking Neural Networks (arxiv.org)
	3 points by PaulHoule 349 days ago \| hide \| past \| pdf \| discuss
2177.	Knowledge Transfer from High-Resource to Low-Resource Languages for Code LLMs (2023) (arxiv.org)
	1 point by peatmoss 349 days ago \| hide \| past \| pdf \| discuss
2178.	OptPipe: Memory- and Scheduling-Optimized Pipeline Parallelism for LLM Training (arxiv.org)
	11 points by PaulHoule 349 days ago \| hide \| past \| pdf \| discuss
2179.	Why can't transformers learn multiplication? (arxiv.org)
	161 points by PaulHoule 349 days ago \| hide \| past \| pdf \| 107 comments
2180.	Prompt Baking (arxiv.org)
	8 points by jxmorris12 349 days ago \| hide \| past \| pdf \| 1 comment
2181.	Binary Retrieval-Augmented Reward Mitigates Hallucinations (arxiv.org)
	44 points by MarlonPro 349 days ago \| hide \| past \| pdf \| 3 comments
2182.	Explaining Why Hallucinate Large Language Models (arxiv.org)
	1 point by gagan30 349 days ago \| hide \| past \| pdf \| 1 comment
2183.	Verifiable ML Without Determinism: Tolerance-Aware Optimistic Verification (arxiv.org)
	1 point by cnyaojz 349 days ago \| hide \| past \| pdf \| 1 comment
2184.	Tensor Logic: The Language of AI (arxiv.org)
	5 points by fofoz 350 days ago \| hide \| past \| pdf \| discuss
2185.	Reasoning with Sampling: Your Base Model Is Smarter Than You Think (arxiv.org)
	3 points by Anon84 350 days ago \| hide \| past \| pdf \| discuss
2186.	Evaluating Agentic Cybersecurity in Attack/Defense CTFs: Offensive Is Not Better (arxiv.org)
	2 points by vmayoral 350 days ago \| hide \| past \| pdf \| 1 comment
2187.	Qwen Language Confusion Gate (arxiv.org)
	2 points by CollinZ 350 days ago \| hide \| past \| pdf \| discuss
2188.	Reasoning with Sampling: Your Base Model Is Smarter Than You Think (arxiv.org)
	2 points by kesor 350 days ago \| hide \| past \| pdf \| discuss
2189.	Modeling Others' Minds as Code (arxiv.org)
	66 points by PaulHoule 350 days ago \| hide \| past \| pdf \| 42 comments
2190.	A Survey of Vibe Coding with Large Language Models (arxiv.org)
	2 points by Anon84 351 days ago \| hide \| past \| pdf \| discuss
	More