A Simple and Effective Pruning Approach for Large Language Models
Comments ICLR 2024. Website at https://eric-mingjie.github.io/wanda/home.html
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking
Comments Poster, ICLR 2024
Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks
Comments ICLR 2024 Spotlight (top 5%)
Verlet Flows: Exact-Likelihood Integrators for Flow-Based Generative Models
Comments ICLR AI4DifferentialEqautions In Science workshop 2024
Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs
Comments Published as a conference paper at ICLR 2024
What does the Knowledge Neuron Thesis Have to do with Knowledge?
Comments ICLR 2024 (Spotlight)
Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy
Comments Accepted as Spotlight Paper for ICLR 2024. The first two authors contributed equally to this work
Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts
Comments Accepted at the Twelfth International Conference on Learning Representations (ICLR 2024)
Neural Structure Learning with Stochastic Differential Equations
Comments ICLR 2024
Privacy Amplification for Matrix Mechanisms
Comments Appearing in ICLR 2024. Changes made to match the conference version of the paper
Improved Active Learning via Dependent Leverage Score Sampling
Comments To appear at ICLR 2024
LLM-grounded Video Diffusion Models
Comments ICLR 2024. Project Page: https://llm-grounded-video-diffusion.github.io/
Guaranteed Approximation Bounds for Mixed-Precision Neural Operators
Comments ICLR 2024
Deep Orthogonal Hypersphere Compression for Anomaly Detection
Comments Published in ICLR 2024: https://openreview.net/pdf?id=cJs4oE4m9Q
A Mutual Information Perspective on Federated Contrastive Learning
Comments Published as a conference paper at ICLR 2024
Stabilizing Backpropagation Through Time to Learn Complex Physics
Comments Published at ICLR 2024, code available at https://github.com/tum-pbs/StableBPTT
Intelligent Switching for Reset-Free RL
Comments Published at ICLR 2024
On the Surprising Efficacy of Distillation as an Alternative to Pre-Training Small Models
Comments ICLR 2024. 5th Workshop on Practical ML for Low Resource Settings (PML4LRS). Code can be found at https://github.com/sfarhat/dapt
Zero-shot generalization across architectures for visual classification
Comments Accepted as a Tiny Paper at ICLR 2024. Code available at https://github.com/dyballa/generalization/tree/ICLR2024TinyPaper
ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation
Comments ICLR 2024 (oral)
Privately Aligning Language Models with Reinforcement Learning
Comments Accepted at ICLR 2024
BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity
Comments ICLR 2024. Project page: https://www.cs.cmu.edu/~afluo/BrainSCUBA
BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models
Comments ICLR 2024 camera-ready version
MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
Comments To appear at ICLR 2024 (Spotlight). Project Page: https://meta-math.github.io/
DORSal: Diffusion for Object-centric Representations of Scenes et al
Comments Accepted to ICLR 2024. Project page: https://www.sjoerdvansteenkiste.com/dorsal
Learning Hierarchical Image Segmentation For Recognition and By Recognition
Comments ICLR 2024 (spotlight). First two authors contributed equally. Code available at https://github.com/twke18/CAST
Towards Unbiased Evaluation of Detecting Unanswerable Questions in EHRSQL
Comments DPFM Workshop, ICLR 2024
Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks
Comments Published at ICLR 2024. Website at https://mihdalal.github.io/planseqlearn/ 9 pages, 3 figures, 3 tables; 14 pages appendix (7 additional figures)
WildChat: 1M ChatGPT Interaction Logs in the Wild
Comments accepted by ICLR 2024
LOQA: Learning with Opponent Q-Learning Awareness
Comments accepted to ICLR but still not in proceedings https://openreview.net/forum?id=FDQF6A1s6M
