Related papers: Beyond Isolated Capabilities: Bridging Long CoT Re…

This paper presents a critical examination of current approaches to replicating OpenAI's O1 model capabilities, with particular focus on the widespread but often undisclosed use of knowledge distillation techniques. While our previous work…

Artificial Intelligence (AI) has increasingly influenced modern society, recently in particular through significant advancements in Large Language Models (LLMs). However, high computational and storage demands of LLMs still limit their…

Recently, deep reinforcement learning (RL) has proven its feasibility in solving combinatorial optimization problems (COPs). The learning-to-rank techniques have been studied in the field of information retrieval. While several COPs can be…

Large language models (LLMs) have shown promising self-correction abilities, where iterative refinement improves the quality of generated responses. However, most existing approaches operate at the level of output critique, patching surface…

Reinforcement learning (RL) is a powerful technique for training intelligent agents, but understanding why these agents make specific decisions can be quite challenging. This lack of transparency in RL models has been a long-standing…

Reasoning-enabled large language models (LLMs) excel in logical tasks, yet their utility for evaluating natural language generation remains unexplored. This study systematically compares reasoning LLMs with non-reasoning counterparts across…

Self-supervised learning solves pretext prediction tasks that do not require annotations to learn feature representations. For vision tasks, pretext tasks such as predicting rotation, solving jigsaw are solely created from the input data.…

Knowledge distillation improves large language model (LLM) reasoning by compressing the knowledge of a teacher LLM to train smaller LLMs. On-policy distillation advances this approach by having the student sample its own trajectories while…

Large Language Models (LLMs) excel at multi-step reasoning problems with explicit chain-of-thought (CoT), but verbose traces incur significant computational costs and memory overhead, and often carry redundant, stylistic artifacts. Latent…

Knowledge distillation is typically realized by transferring a teacher model's knowledge into a student's parameters through supervised or reinforcement-based optimization. While effective, such approaches require repeated parameter updates…

Long-context reasoning has significantly empowered large language models (LLMs) to tackle complex tasks, yet it introduces severe efficiency bottlenecks due to the computational complexity. Existing efficient approaches often rely on…

With the release of R1, a publicly available large reasoning model (LRM), researchers commonly train new LRMs by training language models on R1's long chain-of-thought (CoT) inferences. While prior works show that LRMs' capabilities can be…

Large language model (LLM)-based recommender models that bridge users and items through textual prompts for effective semantic reasoning have gained considerable attention. However, few methods consider the underlying rationales behind…

In many practical applications, large language models (LLMs) need to acquire new knowledge not present in their pre-training data. Efficiently leveraging this knowledge usually relies on supervised fine-tuning or retrieval-augmented…

Large-scale 3D vision-language models (VLMs) like LLaVA-3D offer strong spatial reasoning but are difficult to deploy due to high computational costs. We propose a knowledge distillation framework that transfers spatial reasoning from a 7B…

R1-style Reinforcement Learning (RL) significantly enhances Large Language Models' reasoning capabilities, yet the mechanism behind rule-based RL remains unclear. We found that small-scale SFT has substantial influence on RL but shows poor…

Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, especially when guided by explicit chain-of-thought (CoT) reasoning that verbalizes intermediate steps. While CoT improves both interpretability and accuracy,…

In recent years, the input context sizes of large language models (LLMs) have increased dramatically. However, existing evaluation methods have not kept pace, failing to comprehensively assess the efficiency of models in handling long…

Recent advances in Large Language Models (LLMs) have significantly improved complex reasoning capabilities. Retrieval-Augmented Generation (RAG) has further extended these capabilities by grounding generation in dynamically retrieved…

While large language models (LLMs) excel in mathematical and code reasoning, we observe they struggle with social reasoning tasks, exhibiting cognitive confusion, logical inconsistencies, and conflation between objective world states and…