:: Library Catalog

Copertina

Salvato in:

Dettagli Bibliografici
Autori principali:	Xu, Jiaqi, Lan, Cuiling, Chen, Xuejin, Lu, Yan
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence
Accesso online:	https://arxiv.org/abs/2512.15662
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Long Video Understanding with Learnable Retrieval in Video-Language Models
di: Xu, Jiaqi, et al.
Pubblicazione: (2023)

Slot-VLM: SlowFast Slots for Video-Language Modeling
di: Xu, Jiaqi, et al.
Pubblicazione: (2024)

CSPO: Alleviating Reward Ambiguity for Structured Table-to-LaTeX Generation
di: Yang, Yunfan, et al.
Pubblicazione: (2026)

SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking
di: Huang, Weiyang, et al.
Pubblicazione: (2026)

Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement
di: Yang, Tao, et al.
Pubblicazione: (2024)

TRACE: A Framework for Analyzing and Enhancing Stepwise Reasoning in Vision-Language Models
di: Imani, Shima, et al.
Pubblicazione: (2025)

Interactive Critique-Revision Training for Reliable Structured LLM Generation
di: Yu, Fei Xu, et al.
Pubblicazione: (2026)

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback
di: Zhang, Xiaoying, et al.
Pubblicazione: (2025)

A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting
di: He, Cheng, et al.
Pubblicazione: (2025)

Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning
di: Meherab, Md Muntaqim, et al.
Pubblicazione: (2026)

REMA: A Unified Reasoning Manifold Framework for Interpreting Large Language Model
di: Li, Bo, et al.
Pubblicazione: (2025)

Promoting Efficient Reasoning with Verifiable Stepwise Reward
di: Yue, Chuhuai, et al.
Pubblicazione: (2025)

Stepwise Reasoning Error Disruption Attack of LLMs
di: Peng, Jingyu, et al.
Pubblicazione: (2024)

EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering
di: Xu, Haolei, et al.
Pubblicazione: (2025)

Iterative Critique-Refine Framework for Enhancing LLM Personalization
di: Maram, Durga Prasad, et al.
Pubblicazione: (2025)

Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization
di: Wei, Jiaqi, et al.
Pubblicazione: (2025)

Deciphering Functions of Neurons in Vision-Language Models
di: Xu, Jiaqi, et al.
Pubblicazione: (2025)

STRIDE-ED: A Strategy-Grounded Stepwise Reasoning Framework for Empathetic Dialogue Systems
di: Ji, Hongru, et al.
Pubblicazione: (2026)

LUMIR: an LLM-Driven Unified Agent Framework for Multi-task Infrared Spectroscopy Reasoning
di: Xie, Zujie, et al.
Pubblicazione: (2025)

Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning
di: Tang, Lexiang, et al.
Pubblicazione: (2026)

How Much Thinking is Enough? Quantifying and Understanding Redundancy in LLM Reasoning
di: Zhai, Zhiyuan, et al.
Pubblicazione: (2026)

Teaching AI Stepwise Diagnostic Reasoning with Report-Guided Chain-of-Thought Learning
di: Luo, Yihong, et al.
Pubblicazione: (2025)

Latent Veracity Inference for Identifying Errors in Stepwise Reasoning
di: Kim, Minsu, et al.
Pubblicazione: (2025)

Look as You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning
di: Liu, Shuochen, et al.
Pubblicazione: (2025)

Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback
di: Lin, Yen-Ting, et al.
Pubblicazione: (2025)

CIRCUIT: A Benchmark for Circuit Interpretation and Reasoning Capabilities of LLMs
di: Skelic, Lejla, et al.
Pubblicazione: (2025)

LTM3D: Bridging Token Spaces for Conditional 3D Generation with Auto-Regressive Diffusion Framework
di: Kang, Xin, et al.
Pubblicazione: (2025)

The Critique of Critique
di: Sun, Shichao, et al.
Pubblicazione: (2024)

HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking
di: Gui, Runquan, et al.
Pubblicazione: (2025)

Policy-Guided Stepwise Model Routing for Cost-Effective Reasoning
di: Si, Wenwen, et al.
Pubblicazione: (2026)

The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents
di: Liu, Yuhan, et al.
Pubblicazione: (2024)

Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
di: Qian, Chen, et al.
Pubblicazione: (2025)

MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning
di: Fu, Xiaoliang, et al.
Pubblicazione: (2026)

Reinfier and Reintrainer: Verification and Interpretation-Driven Safe Deep Reinforcement Learning Frameworks
di: Yang, Zixuan, et al.
Pubblicazione: (2024)

Enhancing LLM Reasoning for Time Series Classification by Tailored Thinking and Fused Decision
di: Zhou, Jiahui, et al.
Pubblicazione: (2025)

StepWiser: Stepwise Generative Judges for Wiser Reasoning
di: Xiong, Wei, et al.
Pubblicazione: (2025)

Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning
di: Zhou, Jiahui, et al.
Pubblicazione: (2026)

Bridging Stepwise Lab-Informed Pretraining and Knowledge-Guided Learning for Diagnostic Reasoning
di: Hu, Pengfei, et al.
Pubblicazione: (2024)

Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique
di: Li, Yansi, et al.
Pubblicazione: (2025)

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding
di: Chen, Xi, et al.
Pubblicazione: (2025)