Resources
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Shiyu Ni
December 16, 2025
The existing mechanism and limitations of RLVR, as well as how to use RLVR training to develop models that surpass human-level performance.
View Slides View BlogSmarter Retrieval for Smarter Generation--When and How to Retrieve for Retrieval-Augmented Generation
Keping Bi
November 14, 2025
CIKM 2025 MMGenSR workshop keynote talk.
View Slides View BlogOneRec Technical Report
Lulu Yu
October 28, 2025
OneRec-V1, OneRec-V2 and OneRec-Think.
View Slides View BlogLlama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs
Minghao Tang
October 14, 2025
Llama See Llama Do, an outstanding paper at ACL 2025, finds a novel mechanistic phenomenon termed contextual entrainment, which LMs assign higher logits and probabilities to tokens that appear in the context.
View Slides View BlogEvaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective
Yuchen Wen
September 05, 2025
A psychometrics-inspired attack framework is proposed to reveal implicit biases in large language models(LLMs) via three attack methods, Disguise, Deception, and Teaching.
View Slides View BlogReasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?
Yuhan Wang
September 02, 2025
View SlidesMonitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
Minzhu Tu
July 25, 2025
监控推理模型的不当行为及强化学习中隐蔽奖励作弊的风险
View Slides View BlogCLIP-Based Fine-Grained Image Retrieval Methods
Jiahan Chen
July 17, 2025
基于CLIP的细粒度图像检索方法
View Slides View BlogMassive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
Shiyu Ni
July 06, 2025
自注意力模块中的大值是理解上下文知识的关键
View Slides View BlogConstrained Auto-Regressive Decoding Constrains Generative Retrieval
Changjiang Zhou
June 25, 2025
View SlidesDrawing the Line: Enhancing Trustworthiness of MLLMs Through the Power of Refusal
Zhikai Ding
March 26, 2025
View SlidesParametric Retrieval Augmented Generation
Minghao Tang
March 26, 2025
Parametric RAG proposes a novel paradigm integrating external knowledge as parameters into the feed-forward networks of LLMs.
View SlidesAdversarial ML Problems Are Getting Harder to Solve and to Evaluate
Yuchen Wen
March 19, 2025
View SlidesDeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Qingbin Li
March 05, 2025
View SlidesDeepSeek LLM: Scaling Open-Source Language Models with Longtermism
Da Li
February 26, 2025
View SlidesEvaluating Retrieval Quality in Retrieval-Augmented Generation
Minghao Tang
September 24, 2024
eRAG, SIGIR 2024 best short paper, proposes a new evaluation approach for RAG, using LLM to process each retrieved document individually and evaluates outputs by downstream task labels.
View Slides