J Zico Kolter
~J_Zico_Kolter1
56
论文总数
28.0
年均投稿
平均评分
接收情况36/56
会议分布
ICLR
35
NeurIPS
12
COLM
5
ICML
4
发表论文 (56 篇)
202526 篇
4
Eliciting Black-Box Representations from LLMs through Self-Queries
ICLR 2025Rejected
4
Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance
ICLR 2025Oral
4
Predicting the Performance of Black-box Language Models with Follow-up Queries
NeurIPS 2025Poster
4
Mimetic Initialization Helps State Space Models Learn to Recall
ICLR 2025Rejected
3
The Promises and Pitfalls of Language Models for Structured Numerical Data
ICLR 2025Rejected
5
Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters
ICLR 2025Poster
4
Finetuning CLIP to Reason about Pairwise Differences
ICLR 2025Rejected
5
Understanding Optimization in Deep Learning with Central Flows
ICLR 2025Poster
5
Mean Flows for One-step Generative Modeling
NeurIPS 2025Oral
4
Weight ensembling improves reasoning in language models
COLM 2025Poster
4
Idiosyncrasies in Large Language Models
ICML 2025Poster
4
Data-scarce distillation for large-scale vision language models
ICLR 2025Rejected
4
Prompt Recovery for Image Generation Models: A Comparative Study of Discrete Optimizers
ICLR 2025Rejected
4
Consistency Models Made Easy
ICLR 2025Poster
5
DEQ-MPC : Deep Equilibrium Model Predictive Control
ICLR 2025Rejected
4
Training a Generally Curious Agent
ICML 2025Oral
5
Bayesian Neural Networks with Domain Knowledge Priors
ICLR 2025Rejected
4
Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws
ICLR 2025Poster
4
Contextures: Representations from Contexts
ICML 2025Poster
3
HyperCLIP: Adapting Vision-Language models with Hypernetworks
ICLR 2025Rejected
5
Compute-Optimal LLMs Provably Generalize Better with Scale
ICLR 2025Poster
3
Antidistillation Sampling
NeurIPS 2025Poster
4
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
ICLR 2025Poster
4
Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation
ICLR 2025Rejected
4
Safety Pretraining: Toward the Next Generation of Safe AI
NeurIPS 2025Poster
4
Unnatural Languages Are Not Bugs but Features for LLMs
ICML 2025Poster
202430 篇
4
Why is SAM Robust to Label Noise?
ICLR 2024Poster
4
FUSE-ing Language Models: Zero-Shot Adapter Discovery for Prompt Optimization Across Tokenizers
COLM 2024Poster
4
Diffusing Differentiable Representations
NeurIPS 2024Poster
4
Localized Text-to-Image Generation For Free via Cross Attention Control
ICLR 2024withdrawn
4
Text Descriptions are Compressive and Invariant Representations for Visual Learning
ICLR 2024Rejected
4
On the Joint Interaction of Models, Data, and Features
ICLR 2024Oral
4
Formal Verification for Neural Networks with General Nonlinearities via Branch-and-Bound
ICLR 2024withdrawn
4
Massive Activations in Large Language Models
COLM 2024Poster
4
A Simple and Effective Pruning Approach for Large Language Models
ICLR 2024Poster
4
An Axiomatic Approach to Model-Agnostic Concept Explanations
ICLR 2024Rejected
4
Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression
ICLR 2024Spotlight
4
Projected Off-Policy Q-Learning (POP-QL) for Stabilizing Offline Reinforcement Learning
ICLR 2024Rejected
4
Understanding prompt engineering may not require rethinking generalization
ICLR 2024Poster
4
Understanding Hallucinations in Diffusion Models through Mode Interpolation
NeurIPS 2024Poster
4
Forcing Diffuse Distributions out of Language Models
COLM 2024Poster
5
One-Step Diffusion Distillation through Score Implicit Matching
NeurIPS 2024Poster
3
Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models
NeurIPS 2024Poster
4
Reliable Test-Time Adaptation via Agreement-on-the-Line
ICLR 2024Rejected
4
T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
ICLR 2024Poster
4
Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line
NeurIPS 2024Poster
4
Predicting the Performance of Foundation Models via Agreement-on-the-Line
NeurIPS 2024Poster
4
Predicting the Performance of Foundation Models via Agreement-on-the-line
ICLR 2024Rejected
5
Rethinking LLM Memorization through the Lens of Adversarial Compression
NeurIPS 2024Poster
4
TOFU: A Task of Fictitious Unlearning for LLMs
COLM 2024Poster
4
The Update-Equivalence Framework for Decision-Time Planning
ICLR 2024Poster
3
Computing Low-Entropy Couplings for Large-Support Distributions
ICLR 2024Rejected
5
Improving Alignment and Robustness with Circuit Breakers
NeurIPS 2024Poster
4
Manifold Preserving Guided Diffusion
ICLR 2024Poster
4
Robustness Evaluation of Proxy Models against Adversarial Optimization
ICLR 2024Rejected
3
Enhancing Neural Network Transparency through Representation Analysis
ICLR 2024Rejected