OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypes
Comments Accepted as a Spotlight paper at ICLR 2025
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
Energy-Based Diffusion Language Models for Text Generation
Journal ref ICLR 2025
Equivariant Neural Functional Networks for Transformers
Comments Accepted in ICLR 2025
Demystifying the Token Dynamics of Deep Selective State Space Models
Comments Accepted at ICLR 2025 (spotlight)
F-Fidelity: A Robust Framework for Faithfulness Evaluation of Explainable AI
Comments Accepted to International Conference on Learning Representations (ICLR 2025); 33 Pages, 5 figures, 26 Tables
Efficient Evolutionary Search Over Chemical Space with Large Language Models
Comments Published in ICLR 2025
Bootstrapping Language Models with DPO Implicit Rewards
Comments Accepted in ICLR 2025
Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs
Comments ICLR 2025
Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers
Comments ICLR 2025
DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference
Comments Update DeFT-v4, accepted by ICLR'25 (https://openreview.net/forum?id=2c7pfOqu9k). Our code is available at https://github.com/LINs-lab/DeFT
Learning-Augmented Search Data Structures
Comments ICLR 2025
DEAL-YOLO: Drone-based Efficient Animal Localization using YOLO
Comments Accepted as a Poster at the ML4RS Workshop at ICLR 2025
The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
Comments ICLR 2025 camera-ready version
HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly
Comments ICLR 2025. Project page: https://princeton-nlp.github.io/HELMET/
How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments
Comments Accepted to ICLR 2025; 11 pages of main text; 26 pages of appendices; Included models: GPT-3.5-{0613, 1106, 0125}, GPT-4-0125, GPT-4o-0806, Gemini-{1.0, 1.5)-Pro, LLaMA-3.1-{7, 70, 405}B, Mixtral-8x{7, 22}B, Qwen-2-72B
Know Thy Judge: On the Robustness Meta-Evaluation of LLM Safety Judges
Comments Accepted to the ICBINB Workshop at ICLR'25
Revisiting the Othello World Model Hypothesis
Comments ICLR World Models Workshop
How can representation dimension dominate structurally pruned LLMs?
Comments ICLR 2025 Workshop on Sparsity in LLMs (SLLM)
Large Language Models for Zero-shot Inference of Causal Structures in Biology
Comments ICLR 2025 Workshop on Machine Learning for Genomics Explorations
Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization
Journal ref ICLR 2025
Uncovering Gaps in How Humans and LLMs Interpret Subjective Language
Comments Published at ICLR 2025
Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Ability
Journal ref ICLR 2025
Can We Optimize Deep RL Policy Weights as Trajectory Modeling?
Comments Accepted as an extended abstract to ICLR 2025 Workshop on Weight Space Learning (WSL)
Subgraph Federated Learning for Local Generalization
Comments ICLR 2025 (oral)
Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flows
Comments Accepted to ICLR 2025
CipherPrune: Efficient and Scalable Private Transformer Inference
Comments Accepted by ICLR 2025
Select before Act: Spatially Decoupled Action Repetition for Continuous Control
Comments ICLR 2025
Gated Delta Networks: Improving Mamba2 with Delta Rule
Comments ICLR 2025 camera ready
Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models
Comments Published at ICLR 2025
Gumbel Counterfactual Generation From Language Models
Comments Accepted in ICLR 2025
