NLP Seminar Schedule — Winter 2024
|
| Date | Speaker | Title |
|---|---|---|
| Jan 9 | Tao Yu | From Vision-Language Models to Computer Use Agents: Data, Methods, and Evaluation (details) |
| Jan 16 | Niloofar Mireshghallah | Privacy, Copyright and Data Integrity: The Cascading Implications of Generative AI (details) |
| Jan 23 | Ryan Liu | Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse (details) |
| Feb 6 | Alex Warstadt | Baby Language Models (details) |
| Feb 20 | Aviral Kumar | The Key Ingredients for Scaling Test-Time Compute (internal) |
| Feb 27 | Saadia Gabriel | Simulating Emergent LLM Social Behaviors in Multi-agent Systems (details) |
| Mar 6 | Yun-Nung (Vivian) Chen | Optimizing Interaction and Intelligence -- Multi-Agent Simulation and Collaboration for Personalized Marketing and Advanced Reasoning (details) |
| Mar 13 | Akbir Khan | Multi-Agent Approaches to SuperAlignment (details) |
| Apr 3 | Kayo Yin | NLP for Signed Languages: Challenges and Opportunities (details) |
| Apr 10 | Leonie Weissweiler | Rethinking Linguistic Generalisation in LLMs (details) |
| Apr 17 | Nicholas Tomlin | Reasoning with Language Models (details) |
| May 1 | Neel Nanda | Sparse Autoencoders: Assessing the evidence (details) |
| May 8 | Pratyush Maini | What Memorization Research Taught Me About Safety (details) |
| May 15 | Jacob Andreas | Just asking questions (details) |
| May 22 | Deqing Fu | Closing the Modality Gap: Benchmarking and Improving Visual Understanding in Multimodal LLMs (details) |
| May 29 | Bhuwan Dhingra | Certainty in the face of ambiguity (details) |
We open most talks to the public (even non-stanford affiliates). Stanford affiliates should join nlp-seminar@lists.stanford.edu for weekly announcements. Non-stanford affiliates can follow us on Twitter for announcements and registration.
Organizers: Chenglei Si, Nicole Meister, Sunny Yu
| Date | Speaker | Title |
|---|---|---|
| Oct 3 | Ruiqi Zhong | Concrete Problems in AI Deception: From Evaluation Gaming to Cyber Attack (details) |
| Oct 10 | Harsh Trivedi | AppWorld: Reliable Evaluation of Interactive Agents in a World of Apps and People (details) |
| Oct 17 | Weijia Shi | Beyond Monolithic Language Models (details) |
| Oct 24 | Jieyu Zhao | Building Accountable NLP Models for Social Good (details) |
| Nov 7 | Raj Ammanabrolu | Interactive and Grounded Language Learning (details) |
| Nov 14 | Mengzhou Xia | Aligning Language Models with LESS Data and a Simple (SimPO) Objective (details) |
| Nov 21 | Bill Yuchen Lin | Rethinking LLM Alignment: Mechanisms, Data, and Evaluation (details) |
| Dec 5 | Andrew Lampinen | Grammar, reasoning, learning: Three short stories on comparative & rational analysis of language model capabilities (details) |
We open most talks to the public (even non-stanford affiliates). Stanford affiliates should join nlp-seminar@lists.stanford.edu for weekly announcements. Non-stanford affiliates can follow us on Twitter for announcements and registration.
Organizers: Jing Huang, Weiyan Shi
| Date | Speaker | Title |
|---|---|---|
| July 18 | Robin Jia | Dissecting Large Language Models (details) |
| Aug 1 | Jack Morris | Inverting Language Models (details) |
| Sep 5 | Sander Schulhoff | The State of Prompt Hacking (details) |
We open most talks to the public (even non-stanford affiliates). Stanford affiliates should join nlp-seminar@lists.stanford.edu for weekly announcements. Non-stanford affiliates can follow us on Twitter for announcements and registration.
Organizers: Jing Huang, Weiyan Shi
| Date | Speaker | Title |
|---|---|---|
| Apr 4 | Alane Suhr | Artificial and Natural Language Agents in Interaction (details) |
| Apr 11 | Yuandong Tian | Demystifying Attention Mechanism in Transformer and its application for Large Language Models (details) |
| Apr 18 | Prateek Verma | What Can Small Language Models Teach LLMs and Us (details) |
| Apr 25 | Joyce Chai | Language Communication in Embodied AI: Grounding Matters (details) |
| May 2 | Naomi Saphra | Interpreting Training (details) |
| May 9 | Steven Bird | Must NLP be extractive? (details) |
| May 16 | Karina Nguyen | Language Models: UI Design, Evaluations and Post-training (details) |
| May 23 | Jason Wei | Successful Evals for Large Language Models (details) |
| May 30 | Eve Fleisig | Linguistic Bias in ChatGPT: Language Models Consistently Reinforce Dialect Discrimination (details) |
| June 6 | David Bau | Interpreting transformer LMs: Finding Functions and Facts, and a Fabric (details) |
We open most talks to the public (even non-stanford affiliates). Stanford affiliates should join nlp-seminar@lists.stanford.edu for weekly announcements. Non-stanford affiliates can follow us on Twitter for announcements and registration.
Organizers: Jing Huang, Weiyan Shi
| Date | Speaker | Title |
|---|---|---|
| Jan 11 | Karthik Narasimhan | Language Agents: Past, Present and Future (details) |
| Jan 18 | Hongyuan Mei | Large Language Models as Lego Blocks of Reasoning (details) |
| Jan 25 | Jacob Eisenstein | A Distributional View of Trustworthy Natural Language Processing (details) |
| Feb 1 | Daphne Ippolito | The Challenges of Relying on Language Models Trained on non-Public Data (details) |
| Feb 8 | Been Kim | Alignment and Interpretability - How We Might Get It Right (details) |
| Feb 15 | Peter Hase | Controlling and Editing Knowledge in Large Language Models (details) |
| Feb 22 | Alexander Spangher | NLP Approaches in Computational Journalism: Newsfinding, Sourcing and Updating Stories (details) |
| Feb 29 | Shauli Ravfogel | Identifying and Neutralizing Concepts in Neural Representations (details) |
| Mar 7 | Jennifer Hu | How to Know What Language Models Know (details) |
We open most talks to the public (even non-stanford affiliates). Stanford affiliates should join nlp-seminar@lists.stanford.edu for weekly announcements. Non-stanford affiliates can follow us on Twitter for announcements and registration.
Organizers: Jing Huang, Weiyan Shi
| Date | Speaker | Title |
|---|---|---|
| Sep 28 | Colin Raffel | Build an Ecosystem, Not a Monolith (details) |
| Oct 5 | Nazneen Rajani | Recipe for Training Helpful Chatbots (details) |
| Oct 12 | Tuhin Chakrabarty | Art or Artifice? Large Language Models and the False Promise of Creativity (details) |
| Oct 19 | Tim Althoff | On the Therapeutic Potential of Language Models (details) |
| Oct 26 | Gašper Beguš | AI Interpretability: Finding Causality in Biological and Artificial Communication Systems (details) |
| Nov 2 | Mike Lewis | Towards Pretraining Language Models on Extremely Long Sequences (details) |
| Nov 9 | Jessy Lin | Toward Interactive Agents That Use Language (details) |
| Nov 16 | Anna Ivanova | Dissociating Language and Thought in Large Language Models (details) |
We open most talks to the public (even non-stanford affiliates). Stanford affiliates should join nlp-seminar@lists.stanford.edu for weekly announcements. Non-stanford affiliates can follow us on Twitter for announcements and registration.
Organizers: Siyan Li, Tianyi Zhang
| Date | Speaker | Title |
|---|---|---|
| Apr 6 | Mitchell Wortsman | Robust and accurate fine-tuning for large neural networks (details) |
| Apr 13 | Danqi Chen | Progress and Challenges Towards Building Retrieval-based Language Models (details) |
| Apr 20 | Danish Pruthi | Evaluating Explanations (details) |
| May 4 | Pengcheng Yin | Natural Language to Code Generation for Interactive Data Science (details) |
| May 11 | Lucy Li | Measuring Depictions and Expressions of Social Groups with NLP (details) |
| May 18 | Margaret Li, Suchin Gururangan | Branch-Train-Merge (details) |
| May 25 | Victoria Lin | Large Language Models as Instructable Task Solvers: Lessons Learned and Future Possibilities (details) |
| Jun 1 | Weiyan Shi | Interactive AI Systems Specialized in Social Influence (details) |
We open most talks to the public (even non-stanford affiliates). Stanford affiliates should join nlp-seminar@lists.stanford.edu for weekly announcements. Non-stanford affiliates can follow us on Twitter for announcements and registration.
Organizers: Siyan Li, Tianyi Zhang
| Date | Speaker | Title |
|---|---|---|
| Jan 12 | Chenhao Tan | Towards Human-Centered Explanations of AI Predictions (details) |
| Feb 2 | Yoav Artzi | Learning and Reasoning in Natural Language Interaction (details) |
| Feb 9 | Marco Tulio Ribeiro | Adaptive Testing and Debugging (details) |
| Feb 23 | Oren Tsur | Modeling Decentralized Group Coordination at Large Scale (details) |
| Mar 2 | Denny Zhou | Teach Language Models to Reason (details) |
| Mar 9 | Tiwa Eisape | Probing for Incremental Parse States in Autoregressive Language Models (details) |
| Mar 16 | Boyi Li | Learning from Large Language Models for Grammar Induction (details) |
We open most talks to the public (even non-stanford affiliates). Stanford affiliates should join nlp-seminar@lists.stanford.edu for weekly announcements. Non-stanford affiliates can follow us on Twitter for announcements and registration.
Organizers: Siyan Li, Tianyi Zhang
| Date | Speaker | Title |
|---|---|---|
| Sep 29 | Arya McCarthy | Kilolanguage Learning, Projection, and Translation (details) |
| Oct 6 | Mohit Bansal | Unified and Efficient Multimodal Pretraining Across Vision and Language (details) |
| Oct 13 | Nanyun Peng | Controllable Text Generation For Open-World Creativity (details) |
| Oct 20 | Greg Durrett | Information Synthesis in the Era of GPT-3 (details) |
| Oct 27 | Hanna Hajishirzi | Toward Robust, Multi-Task Natural Language Processing (details) |
| Nov 3 | Mona Diab | Systems and Labeling for Arabic Hate Speech Detection: Challenges and Opportunities (details) |
| Nov 10 | Sebastian Gehrmann | The state of evaluation in NLP (details) |
| Nov 17 | He He | Overcoming spurious correlations in natural language understanding: success and failures (details) |
| Dec 8 | Michiel Bakker | Fine-tuning language models to find agreement among humans with diverse preferences (details) |
We open most talks to the public (even non-stanford affiliates). Stanford affiliates should join nlp-seminar@lists.stanford.edu for weekly announcements. Non-stanford affiliates can follow us on Twitter for announcements and registration.
Organizers: Ashwin Paranjape
| Aug 18 | ||
| Date | Speaker | Title |
|---|---|---|
| Jun 23 | Naomi Saphra | Sources of Variance in Pretraining and Finetuning LLMs (details) |
| Jun 30 | Nouha Dziri | Towards Building Faithful Conversational Models (details) |
| Jul 7 | Jacob Andreas | Toward Natural Language Supervision (details) |
| Aug 11 | Divyansh Kaushik | Resolving the Human Subjects Status of Machine Learning’s Crowdworkers (details) |
Organizers: Ashwin Paranjape
| Date | Speaker | Title |
|---|---|---|
| Mar 31 | Anna Rogers | Challenges in defining and testing machine verbal reasoning skills (details) |
| Apr 7 | Ryan Cotterell | Information-Theoretic Methods in the Study of the Lexicon (details) |
| Apr 14 | Sam Bowman | The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail (details) |
| Apr 21 | Dieuwke Hupkes | Evaluating generalisation in neural networks for NLP (details) |
| Apr 28 | Ethan Perez | Aligning Language Models with Human Preferences (details) |
| May 5 | Eunsol Choi | Information-seeking Language Understanding in a Dynamic World(details) |
| May 19 | David Bamman | Representation in Literary NLP (details) |
| Jun 2 | Róbert Csordás | Principles of Compositionality Improve Systematic Generalization of Neural Network (details) |
Organizers: Ashwin Paranjape, Drew A. Hudson, Rishi Bommasani
| Date | Speaker | Title |
|---|---|---|
| Jan 12 | Florian Strub | Language Emergence at Scale(details) |
| Jan 19 | Jason Wei | Finetuned Language Models are Zero-Shot Learners (details) |
| Feb 10 | Rajarshi Das | Nonparametric Contextual Reasoning for Question Answering over Knowledge Bases (details) |
| Feb 17 | Allyson Ettinger | "Understanding" and prediction: Controlled examinations of meaning sensitivity in pre-trained models (details) |
| Feb 24 | Alane Suhr | Reasoning and Learning in Interactive Natural Language Systems (details) |
| Mar 3 | Krishna Pillutla | MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers (details) |
| Mar 10 | Jeff Dalton and Carlos Gemmell | Conversation Search and Language Understanding: Current Challenges and Future Directions (details) |
| Mar 17 | Chenguang Zhu | How We Achieved Human Parity in CommonsenseQA -- Fusing Knowledge into Language Models |
NLP Seminar Schedule — Fall 2021
|
| Date | Speaker | Title |
|---|---|---|
| Sept 30 | Sonal Gupta | Recent Advances in Fine-Tuning and Question Answering at Facebook Assistant (details) |
| Oct 7 | Marcus Rohrbach | Reasoning with Embeddings and Symbols for Incorporating Knowledge and Reading Comprehension in Vision and Language Tasks (details) |
| Oct 14 | Yoav Levine | Theoretical insights on pretraining Transformers and their practical applications (details) |
| Oct 21 | Luke Zettlemoyer | Large Language Models: Will they keep getting bigger? And, how will we use them if they do? |
| Oct 28 | Tom Hope | Harnessing Scientific Literature for Boosting Discovery and Innovation (details) |
| Nov 4 | Sida Wang | Bilingual lexicon induction via co-occurrences and bitexts (details) |
| Nov 11 | Stefan Lee | Telling Embodied Agents What To Do (And The Agents Sometimes Doing It In Reality) (details) |
| Nov 18 | Sebastian Riedel | |
| Nov 25 | ||
| Dec 2 | Saadia Gabriel | Modeling misinformation, implied toxicity and commonsense implications with machine reasoning (details) |
Organizer: Jesse Mu
| Date | Speaker | Title |
|---|---|---|
| Jan 14 | Ian Tenney | BERTology and Beyond (details) |
| Jan 21 | Roger Levy | Grammatical generalization in neural language models: insights for theory of human language acquisition and processing (details) |
| Jan 28 | NONE (ACL deadline) | |
| Feb 4 | NONE | |
| Feb 11 | Angeliki Lazaridou | Pitfalls of static language modelling (details) |
| Feb 18 | Su Lin Blodgett | Language and Justice: Social Implications of Language Technologies (details) |
| Feb 25 | Ashique KhudaBukhsh | Political Polarization and International Conflicts through the Lens of NLP (details) |
| Mar 4 | Eric Wallace | What Can We Learn From Vulnerabilities of NLP Models? (details, slides) |
| Mar 11 | Forrest Davis | Investigating Competing Training Signals in Language (details) |
| Mar 18 | Elena Voita | NMT Analysis: The Trade-Off Between Source and Target, and (a Bit of) the Training Process (details) |
Organizer: Jesse Mu
| Date | Speaker | Title |
|---|---|---|
| Oct 8 | Jesse Thomason | From Human Language to Agent Action (details, slides) |
| Oct 15 | NONE | |
| Oct 22 | Yoon Kim | Deep Unsupervised Learning of Syntactic Structure (details, slides) |
| Oct 29 | Mikel Artxexe | Unsupervised Machine Translation (details, slides) |
| Nov 5 | Douwe Kiela | Rethinking Benchmarking in AI (details, slides) |
| Nov 12 | Diyi Yang | When Social Context Meets NLP: Learning with Less Data and More Structures (details) |
| Nov 19 | Yonatan Bisk | Language Should be Embodied—But what does that mean? (details, slides) |
| Nov 26 | NONE (thanksgiving) | |
| Dec 3 | Gokhan Tur | Past, Present, Future of Conversational AI (details, slides) |
| Dec 10 | Melanie Subbiah | GPT-3: Few-shot Learning with a Giant Language Model (details, slides) |
Organizer: Kevin Clark
| Date | Speaker | Title |
|---|---|---|
| Jan 23 | Muthu Chandrasekaran | A Discourse Centric Framework for Facilitating Instructor Intervention in MOOC Discussion Forums (details) |
| Jan 30 | Yonatan Belinkov | Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias (details) |
| Feb 6 | Maarten Sap | Reasoning about Social Dynamics in Language (details) |
| Feb 13 | Wojciech Kryściński | Neural Text Summarization: A Critical Perspective and Steps Towards Consistency (details) |
| 20 Feb | Daniel Chen | Stereotypes in High-Stakes Decisions: Evidence from U.S. Circuit Courts (details) |
| 27 Feb | Marco Tulio Ribeiro | What is wrong with my model? Detection and analysis of bugs in NLP models (details) |
| 5 Mar | Roy Schwartz | Green NLP (details) |
| 12 Mar | Jon Clark | TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages (details) REMOTE MEETING |
Organizer: Isabel Papadimitriou
| Date | Speaker | Title |
|---|---|---|
| Sept 26 | Edgar Altszyler | NLP as a means to study individual and social cognition (details) |
| Oct 10 | Bhuwan Dhingra | Text as a Virtual Knowledge Base (details, slides) |
| Oct 17 | Alexis Conneau | Cross-lingual representation learning (details) |
| Nov 14 | Arthur Szlam | Language and Interaction in Minecraft (details) |
| Nov 21 | Michael Auli | Efficient Sequence Modeling (details) |
| Dec 5 | Yoav Artzi | Robot Control and Collaboration in Situated Instruction Following (details, slides) |
Organizer: Dan Iter
| Date | Speaker | Title |
|---|---|---|
| April 4 | Swabha Swayamdipta | Learning Challenges in Natural Language Processing (details, slides) |
| April 11 | Alon Halevy | Subjective Databases (details, slides) |
| April 18 | Paweł Budzianowski | Learning multi-domain dialogues (details, slides) |
| April 25 | Ves Stoyanov | Cross Lingual Understanding (XLU): Scaling NLP Across Languages (details, slides) |
| May 2 | Sameer Singh | Discovering Bugs in NLP Models Using Natural Perturbations (details, slides) |
| May 9 | Xiang Ren | From Data to Model Programming: Injecting Structured Priors for Knowledge Extraction (details) |
| May 16 | Yulia Tsvetkov | Computational Approaches to Unveiling Biases in Stories and Models (details, slides) |
| May 23 | David Bamman | Building an Annotated Dataset of Literary Entities and Events (details, slides) |
Organizer: Dan Iter
| Date | Speaker | Title |
|---|---|---|
| Jan 10 | Liang Huang | STACL: Simultaneous Translation with Integrated Anticipation and Controllable Latency (details, slides) |
| Jan 17 | Jacob Devlin | BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (details, slides) |
| Jan 24 | Anna Goldie | Sequence-to-Sequence Modeling and Deep Reinforcement Learning for Systems Optimization (details, slides) |
| Jan 31 | Chenguang Zhu | SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering (details, slides) |
| Feb 7 | Yu Su | Towards Democratizing Data Science with AI-powered Knowledge Engines (details, slides) |
| Feb 14 | Michael Yeomans | Topic Selection in Conversation (details, slides) |
| Feb 21 | Daniel Fried | Pragmatic Models for Generating and Following Grounded Instructions (details, slides) |
| Feb 28 | Svitlana Volkova | I can’t Believe it’s not Better: Detecting and Quantifying Misinformation and Disinformation (details, slides) |
| Mar 7 | Igor Labutov | Teaching Machines like we Teach People (details, slides) |
| Mar 14 | Rachel Rudinger | Natural Language Understanding for Events and Participants in Text (details) |
Organizer: Dan Iter
| Date | Speaker | Title |
|---|---|---|
| Oct 4 | Bryan McCann | Natural Language Decathlon: Multitask Learning as Question Answering (details, slides) |
| Oct 11 | Luheng He | Semantic Role Labeling with Labeled Span Graph Networks (details, slides) |
| Oct 18 | Shashank Srivastava | Learning Classifiers from Natural Language Explanations (details, slides) |
| Oct 25 | Kai-Wei Chang | What It Takes to Control Societal Bias in Natural Language Processing (details, slides) |
| Nov 1 | Adams Wei Yu | Efficient and Effective Models for Machine Reading Comprehension (details, slides) |
| Nov 8 | Aishwarya Agrawal | Visual Question Answering and Beyond (details, slides) |
| Nov 15 | Nanyun Peng | Building linguistically informed models for low-resource settings (details, slides) |
| Nov 29 | Sida Wang | Building a language interface for data visualization (details) |
Organizer: Siva Reddy
| Date | Speaker | Title |
|---|---|---|
| Jan 11 | Pushpak Bhattacharyya | Sarcasm Detection: A Computational Cognitive Approach (details, slides) |
| Feb 8 | Pararth Shah | Building a Conversational Agent Overnight with Dialogue Self-Play (details, slides) |
| Mar 1 | Gabor Angeli | Conversations, with a reformed academic (details) |
| Mar 8 | Michael Auli | Sequence to Sequence Learning: CNNs, Training and Uncertainty (details, slides) |
| Mar 15 | Jonathan Raiman | Globally Normalized Reader (details, slides) |
| Mar 22 | Dhanya Sridhar | Structured Probabilistic Models for Online Dialogue and Text (details, slides) |
| Apr 12 | Adji Bousso Dieng | Deep Sequence Models: Context Representation, Regularization, and Application to Language (details, slides) |
| May 10 | Alan Ritter | Large Scale Learning for Information Extraction (details, slides) |
| May 24 | Vered Shwartz | Acquiring Lexical Semantic Knowledge (details, slides) |
| Jun 28 | Daniel Khashabi | Reasoning-Driven Question Answering (details, slides) |
| Jul 26 | Will Grathwohl | Backpropagation Through the Void: Optimizing control variates for black-box gradient estimation (details, slides) |
| Aug 9 | Yulia Tsvetkov | Language Generation with Continuous Outputs (details, slides) |
| Aug 16 | Trieu H. Trinh | A Simple Method for Commonsense Reasoning (details, slides) |
| Aug 23 | Ekaterina Shutova | Grasping the finer point: Metaphor identification in text and brain imaging data (details, slides) |
Organizer: Siva Reddy
| Date | Speaker | Title |
|---|---|---|
| Jul 13 | Jason Baldridge | Practical and Ethical Considerations in Demographic and Psychographic Analysis (details, slides) |
| Jul 20 | Lukasz Kaiser | Tensor2Tensor Transformers: New Deep Models for NLP (details, slides) |
| ACL 2017 break | ||
| Aug 17 | Mike Lewis | Deal or No Deal? End-to-End Learning for Negotiation Dialogues (details, slides) |
| Aug 24 | Lea Frermann | Of Space Piracy and Secret Baby Romances: Deep Multi-View Book Representations and a Scalable Evaluation Framework (details, slides) |
| Aug 31 | Jacob Andreas | Structure and Interpretation of Neural Codes (details, slides) |
| EMNLP 2017 break | ||
| Sep 14 | Felix Hill | Grounded language learning in a simulated 3D world (details) |
| Sep 21 | Semester Break | |
| Sep 28 | Cancelled | |
| Oct 5 | Karthik Narasimhan | Language grounding for cross-domain policy transfer and spatial reasoning (details, slides) |
| Oct 19 | Jayant Krishnamurthy | Neural Semantic Parsing with Type Constraints (details, slides) |
| Oct 26 | Zhou Yu | Situated Intelligent Interactive Systems (details, slides) |
| Nov 9 | Eunsol Choi | Scaling Up Reading Comprehension (details, slides) |
| Nov 30 | Nasrin Mostafazadeh | Language Comprehension and Language Generation in Eventful Contexts (details, slides) |