ข่าว
Response-Level Rewards Are All You Need for Online Reinforcement Learning in LLMs: A Mathematical Perspective
arXiv:2506.02553v1 Announce Type: cross Abstract: We study a common challenge in reinforcement learning for large...
Resolving Conflicts in Lifelong Learning via Aligning Updates in Subspaces
arXiv:2512.08960v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) enables efficient Continual Learning but often suffers...
Researchers from the National University of Singapore Introduce ‘Thinkless,’ an Adaptive Framework that Reduces Unnecessary Reasoning by up to 90% Using DeGRPO
The effectiveness of language models relies on their ability to simulate human-like step-by-step deduction. However...
Researchers at UT Austin Introduce Panda: A Foundation Model for Nonlinear Dynamics Pretrained on 20,000 Chaotic ODE Discovered via Evolutionary Search
Chaotic systems, such as fluid dynamics or brain activity, are highly sensitive to initial conditions...
Research on the Integration of Embodied Intelligence and Reinforcement Learning in Textual Domains
arXiv:2510.01076v1 Announce Type: new Abstract: This article addresses embodied intelligence and reinforcement learning integration in...
Research on Multi-hop Inference Optimization of LLM Based on MQUAKE Framework
arXiv:2509.04770v1 Announce Type: new Abstract: Accurately answering complex questions has consistently been a significant challenge...
Representation Decomposition for Learning Similarity and Contrastness Across Modalities for Affective Computing
arXiv:2506.07086v1 Announce Type: new Abstract: Multi-modal affective computing aims to automatically recognize and interpret human...
Repositioning retail for the AI era
Artificial intelligence is rapidly reshaping retail, but not in the ways consumers might immediately notice...
RePo: Language Models with Context Re-Positioning
arXiv:2512.14391v1 Announce Type: cross Abstract: In-context learning is fundamental to modern Large Language Models (LLMs);...
REPA: Russian Error Types Annotation for Evaluating Text Generation and Judgment Capabilities
arXiv:2503.13102v2 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have introduced the...
Rep2Text: Decoding Full Text from a Single LLM Token Representation
arXiv:2511.06571v1 Announce Type: new Abstract: Large language models (LLMs) have achieved remarkable progress across diverse...
Remember Past, Anticipate Future: Learning Continual Multimodal Misinformation Detectors
arXiv:2507.05939v1 Announce Type: new Abstract: Nowadays, misinformation articles, especially multimodal ones, are widely spread on...
