Results 241 to 250 of about 692,148 (292)
Some of the next articles are maybe not open access.
L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
arXiv.orgReasoning language models have shown an uncanny ability to improve performance at test-time by ``thinking longer''-that is, by generating longer chain-of-thought sequences and hence using more compute.
Pranjal Aggarwal, S. Welleck
semanticscholar +1 more source
Reasoning Models Don't Always Say What They Think
arXiv.orgChain-of-thought (CoT) offers a potential boon for AI safety as it allows monitoring a model's CoT to try to understand its intentions and reasoning processes.
Yanda Chen +14 more
semanticscholar +1 more source
Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement
arXiv.orgTraditional methods for reasoning segmentation rely on supervised fine-tuning with categorical labels and simple descriptions, limiting its out-of-domain generalization and lacking explicit reasoning processes.
Yuqi Liu +6 more
semanticscholar +1 more source
2005
AbstractThis chapter examines Hume’s theory of empirical reason, and the difference between its rational and its irrational exercise (reasoning reasonably and unreasonably). The theory has five structural levels: (1) reasoning from one matter of fact or real existence to another takes the form of an inference from an impression to an idea; (2 ...
openaire +1 more source
AbstractThis chapter examines Hume’s theory of empirical reason, and the difference between its rational and its irrational exercise (reasoning reasonably and unreasonably). The theory has five structural levels: (1) reasoning from one matter of fact or real existence to another takes the form of an inference from an impression to an idea; (2 ...
openaire +1 more source
R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization
arXiv.orgLarge Language Models have demonstrated remarkable reasoning capability in complex textual tasks. However, multimodal reasoning, which requires integrating visual and textual information, remains a significant challenge.
Yi Yang +11 more
semanticscholar +1 more source
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
Trans. Mach. Learn. Res.Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks. Recent advancements in Large Reasoning Models (LRMs), such as OpenAI o1 and DeepSeek-R1, have further improved performance in System-2 reasoning domains like ...
Yang Sui +10 more
semanticscholar +1 more source
From System 1 to System 2: A Survey of Reasoning Large Language Models
IEEE Transactions on Pattern Analysis and Machine IntelligenceAchieving human-level intelligence requires refining the transition from the fast, intuitive System 1 to the slower, more deliberate System 2 reasoning.
Zhong-Zhi Li +15 more
semanticscholar +1 more source
SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
Trans. Mach. Learn. Res.This work revisits the dominant supervised fine-tuning (SFT) then reinforcement learning (RL) paradigm for training Large Vision-Language Models (LVLMs), and reveals a key finding: SFT can significantly undermine subsequent RL by inducing ``pseudo ...
Guiming Hardy Chen +7 more
semanticscholar +1 more source
Episteme, 2015
ABSTRACTHilary Kornblith explores the prospects for reasons eliminationism, the view that reasons ought not to be regarded as being of central importance in epistemology. I reply by conceding that reasons may not be necessary for knowledge, in at least some cases, but I argue that they are nevertheless vitally important in epistemology more broadly ...
openaire +1 more source
ABSTRACTHilary Kornblith explores the prospects for reasons eliminationism, the view that reasons ought not to be regarded as being of central importance in epistemology. I reply by conceding that reasons may not be necessary for knowledge, in at least some cases, but I argue that they are nevertheless vitally important in epistemology more broadly ...
openaire +1 more source
Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
arXiv.orgLanguage has long been conceived as an essential tool for human reasoning. The breakthrough of Large Language Models (LLMs) has sparked significant research interest in leveraging these models to tackle complex reasoning tasks.
Fengli Xu +19 more
semanticscholar +1 more source