相关论文: TinyThinker: Distilling Reasoning through Coarse-t…

Large Language Models (LLMs) can transfer their reasoning skills to smaller models by teaching them to generate the intermediate reasoning process required to solve multistep reasoning tasks. While LLMs can accurately solve reasoning tasks…

While large audio language models excel at tasks like ASR and emotion recognition, they still struggle with complex reasoning due to the modality gap between audio and text as well as the lack of structured intermediate supervision. To…

Multimodal sentiment analysis aims to integrate textual, acoustic, and visual information for deep emotional understanding. Despite the progress of multimodal large language models (MLLMs) via supervised fine-tuning, their "black-box"…

Recent thinking models trained with reinforcement learning and backward-checking CoT often suffer from overthinking: they produce excessively long outputs even on simple problems, wasting computation. Existing evaluations, based on token…

Large Language Models (LLMs) have shown impressive capabilities in complex reasoning tasks. However, current approaches employ uniform language density for both intermediate reasoning and final answers, leading to computational…

Tool-integrated reasoning (TIR) has emerged as a dominant paradigm for mathematical problem solving in language models, combining natural language (NL) reasoning with code execution. However, this interleaved setup has three key…

Test-time Training enables model adaptation using only test questions and offers a promising paradigm for improving the reasoning ability of large language models (LLMs). However, it faces two major challenges: test questions are often…

Recent advancements in Large Language Models (LLMs) have leveraged increased test-time computation to enhance reasoning capabilities, a strategy that, while effective, incurs significant latency and resource costs, limiting their…

Recent work has shown that distilling reasoning traces from a larger teacher model via supervised finetuning outperforms reinforcement learning with the smaller student model alone (Guo et al. 2025). However, there has not been a systematic…

Effective code generation with language models hinges on two critical factors: accurately understanding the intent of the prompt and generating code that applies algorithmic reasoning to produce correct solutions capable of passing diverse…

In recent years, many explanation methods have been proposed to explain individual classifications of deep neural networks. However, how to leverage the created explanations to improve the learning process has been less explored. As the…

Reinforcement learning with verifiable rewards improves language model reasoning, but its reliance on domain-specific verifiers, sparse outcome rewards, and coarse-grained credit assignment limits its applicability. We introduce…

We propose a resource-efficient framework for compressing large language models through knowledge distillation, combined with guided chain-of-thought reinforcement learning. Using Qwen 3B as the teacher and Qwen 0.5B as the student, we…

Large reasoning models exhibit remarkable reasoning capabilities via long, elaborate reasoning trajectories. Supervised fine-tuning on such reasoning traces, also known as distillation, can be a cost-effective way to boost reasoning…

Training language models (LMs) and their application agents is increasingly costly due to large datasets and models, making test failures difficult to bear. Simplified language environments serve as primordial training and testing grounds,…

While large models pre-trained on high-quality data exhibit excellent performance on mathematical reasoning (e.g., GSM8k, MultiArith), it remains challenging to specialize smaller models for these tasks. Common approaches to address this…

Large language models (LLMs) demonstrate remarkable reasoning capabilities in tasks such as algorithmic coding and mathematical problem-solving. Recent methods have improved reasoning through expanded corpus and multistage training…

Advanced reasoning in large language models has achieved remarkable performance on challenging tasks, but the prevailing long-context reasoning paradigm faces critical limitations: quadratic computational scaling with sequence length,…

Existing approaches typically rely on large-scale fine-tuning to adapt LLMs for information reranking tasks, which is computationally expensive. In this work, we demonstrate that modern LLMs can be effectively adapted using only minimal,…

Distilling reasoning traces from strong large language models into smaller ones is a promising route to improve intelligence in resource-constrained settings. Existing approaches face a fundamental trade-off: offline distillation from…