← Authors

Tomas Pfister

66 papers · 2015–2026 · 15 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (9) 🌍 Conference Polyglot (14) πŸƒ Academic Marathon (10) πŸŒ‰ Interdisciplinary Bridge 🐝 Cross-Pollinator (9) πŸ—ΊοΈ Taxonomy Completionist (14) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🀝 Dynamic Duo (27) πŸ‘‘ Triple Crown πŸ† Grand Slam πŸ”¬ Deep Specialist (10) 🧬 Topic Evolution πŸ† Keyword Champion (2) ⚑ Prolific Year (9) πŸ—ƒοΈ Keyword Collector (257) πŸ”₯ Unstoppable (7) πŸ’Ž Century Club (65) πŸ“ˆ Trend Setter

Conferences

ACL (12) ICLR (10) CVPR (8) EMNLP (7) NIPS (6) AAAI (4) ECCV (4) ICCV (3) ICML (3) NAACL (3) WACV (2) AISTATS (1) EACL (1) IJCNLP (1) JMLR (1)

Top co-authors

Chen-Yu Lee (28) Chun-Liang Li (20) Zifeng Wang (16) Zizhao Zhang (13) Sercan Arik (12) Jinsung Yoon (11) Long Le (10) Ruoxi Sun (9) Vincent Perot (9) Kihyuk Sohn (8)

Keywords

large language model (12) zero-shot learning (6) knowledge distillation (5) unsupervised learning (5) retrieval-augmented generation (4) question answering (4) information retrieval (3) representation learning (3) document understanding (3) in-context learning (3) information extraction (3) neural network (3) language model (3) domain adaptation (3) reinforcement learning (3) model compression (2) multimodal learning (2) text generation (2) data augmentation (2) anomaly detection (2)

Papers

SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback EACL 2026
Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment ICLR 2025
Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling ICLR 2025
Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence ICML 2025
Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting ICLR 2025
Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training ICLR 2025
Reverse Thinking Makes LLMs Stronger Reasoners NAACL 2025
PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving EMNLP 2025
PLAN-TUNING: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solving EMNLP 2025
In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents ACL 2025
Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph Translation ACL 2025
TableRAG: Million-Token Table Understanding with Language Models NIPS 2024
Effective Large Language Model Adaptation for Improved Grounding and Citation Generation NAACL 2024
TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting ICLR 2024
Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning ICML 2024
Matryoshka-Adaptor: Unsupervised and Supervised Tuning for Smaller Embedding Dimensions EMNLP 2024
Search-Adaptor: Embedding Customization for Information Retrieval ACL 2024
Chain of Agents: Large Language Models Collaborating on Long-Context Tasks NIPS 2024
Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrieval EMNLP 2024
CodecLM: Aligning Language Models with Tailored Synthetic Data NAACL 2024
CaLM: Contrasting Large and Small Language Models to Verify Grounded Generation ACL 2024
TextGenSHAP: Scalable Post-Hoc Explanations in Text Generation with Long Documents ACL 2024
Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding ICLR 2024
Found in the middle: Calibrating Positional Attention Bias Improves Long Context Utilization ACL 2024
Universal Self-Adaptive Prompting EMNLP 2023
Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs EMNLP 2023
Unifying Distribution Alignment as a Loss for Imbalanced Semi-Supervised Learning WACV 2023
Neural Spline Search for Quantile Probabilistic Modeling AAAI 2023
Anomaly Clustering: Grouping Images Into Coherent Clusters of Anomaly Types WACV 2023
FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction ACL 2023
Better Zero-Shot Reasoning with Self-Adaptive Prompting ACL 2023
QueryForm: A Simple Zero-shot Form Entity Query Framework ACL 2023
Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes ACL 2023
Prefix Conditioning Unifies Language and Label Supervision CVPR 2023
Pic2Word: Mapping Pictures to Words for Zero-Shot Composed Image Retrieval CVPR 2023
SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Data EMNLP 2023
DualPrompt: Complementary Prompting for Rehearsal-Free Continual Learning ECCV 2022
Learning from Weakly-Labeled Web Videos via Exploring Sub-concepts AAAI 2022
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding AAAI 2022
FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction ACL 2022
Decoupling Local and Global Representations of Time Series AISTATS 2022
Learning To Prompt for Continual Learning CVPR 2022
Learning Instance-Specific Adaptation for Cross-Domain Segmentation ECCV 2022
Learning Fast Sample Re-Weighting Without Reward Data ICCV 2021
Learning and Evaluating Representations for Deep One-Class Classification ICLR 2021
CutPaste: Self-Supervised Learning for Anomaly Detection and Localization CVPR 2021
PseudoSeg: Designing Pseudo Labels for Semantic Segmentation ICLR 2021
TabNet: Attentive Interpretable Tabular Learning AAAI 2021
ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction ACL 2021
ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction IJCNLP 2021
Controlling Neural Networks with Rule Representations NIPS 2021
Differentiable Top-k with Optimal Transport NIPS 2020
Distance-Based Learning from Errors for Confidence Calibration ICLR 2020
Interpretable Sequence Learning for Covid-19 Forecasting NIPS 2020
Learning to Transfer Learn: Reinforcement Learning-Based Selection for Adaptive Transfer Learning ECCV 2020
Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost ECCV 2020
Distilling Effective Supervision From Severe Label Noise CVPR 2020
Data Valuation using Reinforcement Learning ICML 2020
ProtoAttend: Attention-Based Prototypical Learning JMLR 2020
On Completeness-aware Concept-Based Explanations in Deep Neural Networks NIPS 2020
Inserting Videos Into Videos CVPR 2019
Harmonic Unpaired Image-to-image Translation ICLR 2019
Generative Modeling for Small-Data Object Detection ICCV 2019
Learning From Simulated and Unsupervised Images Through Adversarial Training CVPR 2017
Personalizing Human Video Pose Estimation CVPR 2016
Flowing ConvNets for Human Pose Estimation in Videos ICCV 2015