English
Related papers

Related papers: CRANE: Constrained Reasoning Injection for Code Ag…

200 papers

Self-training approach for large language models (LLMs) improves reasoning abilities by training the models on their self-generated rationales. Previous approaches have labeled rationales that produce correct answers for a given question as…

Machine Learning · Computer Science 2025-02-07 Jaehyeok Lee , Keisuke Sakaguchi , JinYeong Bak

Recent advances in reinforcement learning (RL) using numerical rewards have significantly enhanced the complex reasoning capabilities of large language models (LLMs). However, we identify three fundamental limitations of purely numerical…

Computation and Language · Computer Science 2026-02-23 Xiaoying Zhang , Yipeng Zhang , Hao Sun , Kaituo Feng , Chaochao Lu , Chao Yang , Helen Meng

Reasoning models think out loud, but much of what they say is noise. We introduce CRISP (Compressed Reasoning via Iterative Self-Policy Distillation), a method that teaches models to reason more concisely by distilling their own concise…

Machine Learning · Computer Science 2026-04-14 Hejian Sang , Yuanda Xu , Zhengze Zhou , Ran He , Zhipeng Wang , Jiachen Sun

While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it requires models to verbalize every intermediate step in text tokens, constraining the model thoughts to the discrete vocabulary…

Computation and Language · Computer Science 2026-02-12 Weihao Liu , Dehai Min , Lu Cheng

Concept unlearning aims to erase a target concept from a pretrained text-to-image diffusion model without retraining. Closed-form methods are attractive in this setting because they apply a single deterministic edit to the cross-attention…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Saemi Moon , Suhyeon Jun , Seoyeon Lee , Dongwoo Kim

Reinforcement learning (RL) training of large language models (LLMs) on unverifiable tasks is challenging even when a reasonable-quality reference answer is available. We propose a constrained RL training framework that (i) optimizes a…

Language models can be used to provide interactive, personalized student feedback in educational settings. However, real-world deployment faces three key challenges: privacy concerns, limited computational resources, and the need for…

Computation and Language · Computer Science 2025-10-31 Fares Fawzi , Vinitra Swamy , Dominik Glandorf , Tanya Nazaretsky , Tanja Käser

Most sentence embedding techniques heavily rely on expensive human-annotated sentence pairs as the supervised signals. Despite the use of large-scale unlabeled data, the performance of unsupervised methods typically lags far behind that of…

Computation and Language · Computer Science 2022-11-01 Yiming Chen , Yan Zhang , Bin Wang , Zuozhu Liu , Haizhou Li

Multi-constraint planning involves identifying, evaluating, and refining candidate plans while satisfying multiple, potentially conflicting constraints. Existing large language model (LLM) approaches face fundamental limitations in this…

Artificial Intelligence · Computer Science 2026-01-26 Derrick Goh Xin Deik , Quanyu Long , Zhengyuan Liu , Nancy F. Chen , Wenya Wang

Recent progress in reasoning with large language models (LLMs), such as DeepSeek-R1, demonstrates impressive capabilities in domains like mathematics and coding, by exhibiting complex cognitive behaviors such as verification, goal…

Artificial Intelligence · Computer Science 2025-10-14 Xiao Yu , Baolin Peng , Ruize Xu , Michel Galley , Hao Cheng , Suman Nath , Jianfeng Gao , Zhou Yu

Recent advances in large language models (LLMs), such as OpenAI-o1 and DeepSeek-R1, have demonstrated the effectiveness of test-time scaling, where extended reasoning processes substantially enhance model performance. Despite this, current…

Computation and Language · Computer Science 2025-03-26 Xiaoyu Tian , Sitong Zhao , Haotian Wang , Shuaiting Chen , Yunjie Ji , Yiping Peng , Han Zhao , Xiangang Li

Large language models handle single-turn generation well, but multi-turn interactions still require the model to reconstruct user intent and task state from an expanding token history because internal representations do not persist across…

Computation and Language · Computer Science 2025-12-11 Vishwas Hegde , Vindhya Shigehalli

We introduce CoreThink, a state-of-the-art Reasoning Layer built upon a novel reasoning method called General Symbolics. This approach diverges from reasoning paradigms such as test-time scaling, Supervised Fine-Tuning (SFT), and…

Artificial Intelligence · Computer Science 2025-09-04 Jay Vaghasiya , Omkar Ghugarkar , Vishvesh Bhat , Vipul Dholaria , Julian McAuley

Universal Multimodal Retrieval requires unified embedding models capable of interpreting diverse user intents, ranging from simple keywords to complex compositional instructions. While Multimodal Large Language Models (MLLMs) possess strong…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Xiangzhao Hao , Shijie Wang , Tianyu Yang , Tianyue Wang , Haiyun Guo , Jinqiao Wang

Mixture-of-Experts (MoE) enables efficient scaling of large language models by activating only a subset of experts per input token. However, deploying MoE-based models incurs significant memory overhead due to the need to retain all experts…

Machine Learning · Computer Science 2026-02-24 Geng Zhang , Yuxuan Han , Yuxuan Lou , Yiqi Zhang , Wangbo Zhao , Yang You

Current autoregressive language models (ARMs) achieve high accuracy but require long token sequences, making them costly. Discrete diffusion language models (DDLMs) enable parallel and flexible generation within a fixed number of steps and…

Computation and Language · Computer Science 2025-10-21 Lina Berrayana , Ahmed Heakl , Muhammad Abdullah Sohail , Thomas Hofmann , Salman Khan , Wei Chen

On-policy self-distillation (self-OPD) densifies reinforcement learning with verifiable rewards (RLVR) by letting a policy teach itself under privileged context. We find that when this guidance spans the full response, all-token KL spends…

Artificial Intelligence · Computer Science 2026-05-12 Jiaxuan Wang , Xuan Ouyang , Zhiyu Chen , Yulan Hu , Zheng Pan , Xin Li , Lan-Zhe Guo

Large language models (LLMs) achieve strong performance by generating long chains of thought, but longer traces always introduce redundant or ineffective reasoning steps. One typical behavior is that they often perform unnecessary…

Computation and Language · Computer Science 2026-01-13 Jinyi Han , Zixiang Di , Zishang Jiang , Ying Liao , Jiaqing Liang , Yongqi Wang , Yanghua Xiao

Large language models often fail on multi-step reasoning due to fixed reasoning strategies that ignore problem specific difficulty. We introduce CARD (Complexity Agnostic Recursive Decomposition), a framework that predicts problem…

Computation and Language · Computer Science 2026-01-09 Kaleem Ullah Qasim , Jiashu Zhang , Hafiz Saif Ur Rehman

As artificial intelligence (AI) applications continue to expand in next-generation networks, there is a growing need for deep neural network (DNN) models. Although DNN models deployed at the edge are promising for providing AI as a service…

Networking and Internet Architecture · Computer Science 2024-08-22 Alireza Maleki , Hamed Shah-Mansouri , Babak H. Khalaj
‹ Prev 1 8 9 10 Next ›