Activities ▸ Lab Meeting
Lab members work on a variety of research projects. The Lab Meeting provides a weekly opportunity to share their work with other lab members and get their feedback.
Logistics
- Lab-wide announcement (15 min.)
- Everyone’s submission plan
- Brief recap of conference deadlines
- Discussion about lab management
- Paper skimming (weekly)
- 3 people presents their favorite papers (15 min. x 3)
- Talk: 5 min. / QA : 10 min.
- Poster presentation (monthly)
- 4-5 people present their work by a poster
- Spotlight presentation(s) (on demand)
- 1-2 people present their relatively complete work in oral presentation
Meetings Log
Date | Presenters | Topic | URL | Authors |
---|---|---|---|---|
09/03/2025 | A Akira Ishii | Mid-Term Presentation Practice | ||
09/02/2025 | P Peter_Obule | Mid-Term Presentation Practice | ||
08/08/2025 | T Tien Dang Huu | MS Defense Practice | ||
07/25/2025 | A Akira Ishii | Paper Skimming: 1.VISUAL ATTENTION SINK IN LARGE MULTIMODAL MODELS 2. A Causal Approach for Counterfactual Reasoning in Narratives | 1. See What You Are Told: Visual Attention Sink in Large Multimodal Models | OpenReview 2. 2024.acl-long.354/ | 1. Seil Kang, Jinyeong Kim, Junhyeok Kim, Seong Jae Hwang 2. Feiteng Mu, Wenjie Li |
07/18/2025 | K Kim Pothong N NGUYEN Phuong Minh | Paper Skimming: 1. 2. 3. INSTRUCTSCORE: Towards Explainable Text Generation Evaluation with Automatic Feedback | 1. 235/liu24bn.html 2. 2506.09047 3. INSTRUCTSCORE: Towards Explainable Text Generation Evaluation with Automatic Feedback - ACL Anthology | 1. Shih-Yang Liu, Chien-Yi Wang, Hongxu Yin, Pavlo Molchanov, Yu-Chiang Frank Wang, Kwang-Ting Cheng, Min-Hung Chen 2. Yaniv Nikankin, Dana Arad, Yossi Gandelsman, Yonatan Belinkov 3. Wenda Xu, Danqing Wang, Liangming Pan, Zhenqiao Song, Markus Freitag, William Wang, Lei Li |
07/11/2025 | Poster Presentation: 1. Counting First or Detection First? An Investigation on Counting Objects in LVLMs 2. The Transfer Neurons Hypothesis: An Underlying Mechanism for Language Subspace Transitions in Multilingual LLMs | |||
07/04/2025 | P Peter_Obule | Paper Skimming: 1. DOLA: DECODING BY CONTRASTING LAYERS IMPROVES FACTUALITY IN LARGE LANGUAGE MODELS 2. Mission: Impossible Language Models 3.Neuron-Level Knowledge Attribution in Large Language Models | 1. DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models | OpenReview 2. Mission: Impossible Language Models - ACL Anthology 3. Neuron-Level Knowledge Attribution in Large Language Models - ACL Anthology | 1. Yung-Sung Chuang~Yung-Sung_Chuang1, Yujia Xie, Hongyin Luo, Yoon Kim, James R. Glass, Pengcheng He 2. Julie Kallini, Isabel Papadimitriou, Richard Futrell, Kyle Mahowald, Christopher Potts 3. Zeping Yu, Sophia Ananiadou |
06/27/2025 | Paper Skimming: 1. Understanding In-context Learning of Addition via Activation Subspaces, 2. Paper Skimming: The Origins of Representation Manifolds in Large Language Models, 3. Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals | 1. 2505.05145v2 2. 2505.18235 3. 2402.11655v2 | 1. Xinyan Hu, Kayo Yin, Michael I. Jordan, Jacob Steinhardt, Lijie Chen 2. Alexander Modell, Patrick Rubin-Delanchy, Nick Whiteley 3. Francesco Ortu, Zhijing Jin, Diego Doimo, Mrinmaya Sachan, Alberto Cazzaniga, Bernhard Schölkopf | |
06/20/2025 | A Akira IshiiT TRAN, Thu Thi Anh | Paper Skimming: 1. FACTTRACK: Time-Aware World State Tracking in Story Outlines 2. Mitigating Catastrophic Forgetting in Large Language Models
with Self-Synthesized Rehearsal 3. Distillation Scaling Laws | 1. 2025.naacl-long.144 2. 2403.01244v2 3. 2502.08606v2 | 1. Zhiheng Lyu, Kevin Yang, Lingpeng Kong, and Dan Klein 2. Jianheng Huang, Leyang Cui, Ante Wang, Chengyi Yang, Xinting Liao, Linfeng Song, Junfeng Yao, Jinsong Su 3. Dan Busbridge, Amitis Shidani, Floris Weers, Jason Ramapuram, Etai Littwin, Russ Webb |
06/13/2025 | T Tien Dang Huu | Poster Presentation: 1.On Effects of Steering Latent Representation for Large Language Model Unlearning; 2.Step-wise Decomposition Improves Calibration for Answering Multi-Hop Questions | ||
05/30/2025 | P Peter_Obule | Paper Skimming: 1. LEGEND: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets 2.Understanding the Emergence of Multimodal Representation Alignment | 1. 2406.08124v2 2. 2502.16282v2 | 1. Duanyu Feng, Bowen Qin, Chen Huang, Youcheng Huang, Zheng Zhang, Wenqiang Lei 2. Megan Tjandrasuwita, Chanakya Ekbote, Liu Ziyin, Paul Pu Liang |
05/23/2025 | Paper Skimming: 1. Inferring Functionality of Attention Heads from their Parameters; 2.From Tokens to Words: On the Inner Lexicon of LLMs | 1. 2412.11965v2 2. 2410.05864v4 | 1. Amit Elhelo, Mor Geva 2. Guy Kaplan, Matanel Oren, Yuval Reif, Roy Schwartz | |
05/16/2025 | Paper Skimming: 1. Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations; 2. Confidence Regulation in LLMs; 3.Massive Values in SA are the Key to Contextual Knowledge Understanding | 1. 2410.02762v2 2. 2406.16254v2 3. Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding | 1. Nick Jiang, Anish Kachinthaya, Suzie Petryk, Yossi Gandelsman 2. Alessandro Stolfo, Ben Wu, Wes Gurnee, Yonatan Belinkov, Xingyi Song, Mrinmaya Sachan, Neel Nanda 3. Mingyu Jin, Kai Mei, Wujiang Xu, Mingjie Sun, Ruixiang Tang, Mengnan Du, Zirui Liu, Yongfeng Zhang | |
05/09/2025 | K Kim Pothong | Poster Presentation: 1. Mechanism Interpretability on ICL; 2. FOCUS Benchmark;3. Understanding Compositional Visual Reasoning | ||
04/25/2025 | N NGUYEN Phuong MinhK Kim Pothong | Paper Skimming: 1. ; 2. 3.Text Generation Evaluation Survey and Kim’s Opinion | 1. pdf 2. 2311.03533v1 3. 2006.14799 | 1. Xi Ye Qiaochu Chen Isil Dillig Greg Durrett 2. Sree Harsha Tanneru, Chirag Agarwal, Himabindu Lakkaraju 3. Asli Celikyilmaz, Elizabeth Clark, Jianfeng Gao |
04/18/2025 | T TRAN, Thu Thi AnhP Peter_Obule | Paper Skimming: 1. Iterative Refinement of Project-Level Code Generation; 2. Attention as a HyperNetwork; 3. Inference Time Intervention: Eliciting Truthful Answer from a Language Model | 1. Zhangqian Bi, Yao Wan, Zheng Wang, Hongyu Zhang, Batu Guan, Fangxin Lu, Zili Zhang, Yulei Sui, Hai Jin, Xuanhua Shi 2. Simon Schug, Seijin Kobayashi, Yassir Akram, João Sacramento, Razvan Pascanu 3. Kenneth Li, Oam Patel, Fernanda Viégas, Hanspeter Pfister, Martin Wattenberg | |
04/11/2025 | T Tien Dang HuuA Akira Ishii | Paper Skimming: 1. Confidence Regulation Neurons in LMs; 2. Unlearning in LLMs: An Introduction; 3. Story Embeddings—Narrative-Focused Representations of Fictional Stories | 1. Alessandro Stolfo, Ben Wu, Wes Gurnee, Yonatan Belinkov, Xingyi Song, Mrinmaya Sachan, Neel Nanda 2. Tien Dang Huu 3. Hans Ole Hatzel and Chris Biemann. | |
04/04/2025 | Kick-off Meeting | |||
03/03/2025 | K Kim Pothong | NLP2025 Practice Presentation | ||
02/20/2025 | NLP 2025 Practice Presentation | |||
02/13/2025 | Revisiting In-context Learning Inference Circuit in Large Lan- guage Models (ICLR 2025) | |||
02/06/2025 | ||||
01/30/2025 | S Shotaro Kitamura | Quick walkthrough: running Llama on Kagayaki | ||
01/23/2025 | Brainstorming on Logo Design | |||
01/16/2025 | General Discussions | |||
12/11/2024 | Probing Implicit Multi-Step Reasoning in Visual-Language Models | |||
11/27/2024 | Y Yan_zhenzhu | Research Proposal: Traffic Sign Benchmarking | ||
11/20/2024 | Light Hearted Mechanistic Interpretability | |||
11/13/2024 | UI Operation Agent | |||
10/30/2024 | K Kim Pothong | Leveraging Socratic Feedback: Using Counter-Arguments to Argument Revision | ||
10/23/2024 | T TRAN, Thu Thi Anh | (Master’s Thesis Recap) Towards x86 Instruction Set Emulation in Java via Project-based Text-to-Code Generation using Reinforcement Learning | ||
10/16/2024 | S SAKAI Yoshihiro | Speech Title: Improve your Presentation | ||
10/08/2024 | Kick-off Meeting | |||
09/24/2024 | Image Encodings are Informative Tokens for Frozen Text Transformers | |||
09/03/2024 | Practice for Mid-term Presentation | |||
08/27/2024 | YANS Practice Talk | |||
08/06/2024 | Practice Talk for MS Defense | |||
07/16/2024 | Flee the Flaw: Annotating the Underlying Logic of Fallacious Arguments Through Templates and Slot-filling | |||
07/09/2024 | Special Session: 2nd Kick-off! | |||
07/02/2024 | Probing Visual Prompts in Multimodal Large Language Models (MLLMs) | |||
06/25/2024 | K Kim Pothong | NL260 Practice Talk x 2 | ||
06/18/2024 | Meta Cognitive Knowledge in LLMs | |||
05/28/2024 | S Shotaro Kitamura | Towards Making Japanese Implicit Multi-hop Question Benchmarks | ||
05/21/2024 | Y Yan_zhenzhu | A Survey of Vision Language Model in Autonomous Driving | ||
05/14/2024 | How to Make Explanation Behind Visual Reasoning Response of LVLMs | |||
05/07/2024 | K Kim Pothong | FA1A2 - A Dataset of Fallacious/Non-Fallacious Arguments for LLM Probing | ||
04/22/2024 | A Survey of the Latest GUI Agent for Cross Application Task and Progress Report | |||
04/16/2024 | Word Embedding “Geometry” | |||
04/10/2024 | T Tien Dang Huu | Machine Unlearning: Setting, Benchmark, Evaluation | ||
04/04/2024 | Kick-off Meeting | |||
03/04/2024 | (NLP2024 poster & presentation practice #2) | |||
02/29/2024 | NLP2024 poster & presentation practice #1 | |||
02/22/2024 | Practice talk for mid-term presentation | |||
02/21/2024 | S Shotaro Kitamura | Practice talk for mid-term presentation | ||
02/08/2024 | Practice talk for MS thesis defense | |||
02/01/2024 | Self-Awareness Improves Reliability of LM as KB | |||
01/25/2024 | K Kim Pothong | Fallacies Detection Exploitation Toward Large Language Model | ||
01/18/2024 | Can Data Augmentation with Predicate Logic Extend the Predicate Logic Inference of LLM? | |||
01/11/2024 | T Tien Dang Huu | Machine Unlearning: Similarity-based methods | ||
12/21/2023 | S SAKAI Yoshihiro | In-Context Learning | ||
12/12/2023 | A Akira Ishii | Identify Important Event in Narrative | ||
12/05/2023 | Various Probing on VLMs | |||
11/28/2023 | Why My Argument has Fallacy | |||
11/21/2023 | (Only Announcement) | |||
11/14/2023 | Entailment Tree Construction: Step-by-Step Approach Using Large Language Models | |||
11/07/2023 | S Shotaro Kitamura | Towards Making Better Implicit Multi-hop QA Benchmark | ||
10/31/2023 | Non-end-to-end Evaluation Approaches for Visual Reasoning | |||
10/17/2023 | A Comprehensive (maybe) Survey / Intro about ICL Theory | |||
10/10/2023 | Kick-off Meeting | |||
10/02/2023 | The Rise and Potential of Large Language Model Based Agents: A Survey | |||
09/05/2023 | Practice Talk for Mid-term Presentation | |||
08/07/2023 | From traditional VL to MLLMs | |||
07/24/2023 | (Only Announcement) | |||
07/18/2023 | Controller of LLM for Multi-step Reasoning | |||
07/03/2023 | Like Father, Like Son: Large Language Models Empower Smaller Language Models for Zero Shot Fallacy Detection | |||
06/26/2023 | Let’s Watch Together: “How to Read/Write an International Conference Paper by Prof. Graham Neubig@CMU” | |||
06/19/2023 | Towards Inductive Reasoning from Visual Information | |||
06/14/2023 | S Shotaro Kitamura | Research Progress Report: Towards generating Japanese multi-hop QA Datasets | ||
05/29/2023 | (Only Announcement) | |||
05/22/2023 | [Paper Reading] Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models | |||
05/15/2023 | Self-Instruct_ Aligning LM with Self Generated Instructions | |||
05/08/2023 | H Hoai Linh Luu | Improving Robustness of NLP Models by Explanation-based Feedback | ||
04/12/2023 | Kick-off Meeting |