PaperHub

J Zico Kolter

~J_Zico_Kolter1

56
论文总数
28.0
年均投稿
5.8
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

6.0
4

Eliciting Black-Box Representations from LLMs through Self-Queries

ICLR 2025Rejected
8.0
4

Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance

ICLR 2025Oral
7.3
4

Predicting the Performance of Black-box Language Models with Follow-up Queries

NeurIPS 2025Poster
4.5
4

Mimetic Initialization Helps State Space Models Learn to Recall

ICLR 2025Rejected
5.3
3

The Promises and Pitfalls of Language Models for Structured Numerical Data

ICLR 2025Rejected
5.8
5

Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters

ICLR 2025Poster
5.3
4

Finetuning CLIP to Reason about Pairwise Differences

ICLR 2025Rejected
7.0
5

Understanding Optimization in Deep Learning with Central Flows

ICLR 2025Poster
7.8
5

Mean Flows for One-step Generative Modeling

NeurIPS 2025Oral
7.0
4

Weight ensembling improves reasoning in language models

COLM 2025Poster
5.5
4

Idiosyncrasies in Large Language Models

ICML 2025Poster
5.0
4

Data-scarce distillation for large-scale vision language models

ICLR 2025Rejected
3.0
4

Prompt Recovery for Image Generation Models: A Comparative Study of Discrete Optimizers

ICLR 2025Rejected
6.8
4

Consistency Models Made Easy

ICLR 2025Poster
4.6
5

DEQ-MPC : Deep Equilibrium Model Predictive Control

ICLR 2025Rejected
7.8
4

Training a Generally Curious Agent

ICML 2025Oral
5.4
5

Bayesian Neural Networks with Domain Knowledge Priors

ICLR 2025Rejected
5.5
4

Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws

ICLR 2025Poster
5.5
4

Contextures: Representations from Contexts

ICML 2025Poster
4.0
3

HyperCLIP: Adapting Vision-Language models with Hypernetworks

ICLR 2025Rejected
6.0
5

Compute-Optimal LLMs Provably Generalize Better with Scale

ICLR 2025Poster
6.4
3

Antidistillation Sampling

NeurIPS 2025Poster
6.8
4

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

ICLR 2025Poster
5.0
4

Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation

ICLR 2025Rejected
6.8
4

Safety Pretraining: Toward the Next Generation of Safe AI

NeurIPS 2025Poster
4.9
4

Unnatural Languages Are Not Bugs but Features for LLMs

ICML 2025Poster

202430

6.0
4

Why is SAM Robust to Label Noise?

ICLR 2024Poster
6.0
4

FUSE-ing Language Models: Zero-Shot Adapter Discovery for Prompt Optimization Across Tokenizers

COLM 2024Poster
5.0
4

Diffusing Differentiable Representations

NeurIPS 2024Poster
4.3
4

Localized Text-to-Image Generation For Free via Cross Attention Control

ICLR 2024withdrawn
4.8
4

Text Descriptions are Compressive and Invariant Representations for Visual Learning

ICLR 2024Rejected
7.5
4

On the Joint Interaction of Models, Data, and Features

ICLR 2024Oral
5.3
4

Formal Verification for Neural Networks with General Nonlinearities via Branch-and-Bound

ICLR 2024withdrawn
6.5
4

Massive Activations in Large Language Models

COLM 2024Poster
6.3
4

A Simple and Effective Pruning Approach for Large Language Models

ICLR 2024Poster
3.0
4

An Axiomatic Approach to Model-Agnostic Concept Explanations

ICLR 2024Rejected
6.8
4

Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression

ICLR 2024Spotlight
4.0
4

Projected Off-Policy Q-Learning (POP-QL) for Stabilizing Offline Reinforcement Learning

ICLR 2024Rejected
7.5
4

Understanding prompt engineering may not require rethinking generalization

ICLR 2024Poster
4.8
4

Understanding Hallucinations in Diffusion Models through Mode Interpolation

NeurIPS 2024Poster
6.3
4

Forcing Diffuse Distributions out of Language Models

COLM 2024Poster
6.8
5

One-Step Diffusion Distillation through Score Implicit Matching

NeurIPS 2024Poster
5.7
3

Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models

NeurIPS 2024Poster
5.5
4

Reliable Test-Time Adaptation via Agreement-on-the-Line

ICLR 2024Rejected
6.5
4

T-MARS: Improving Visual Representations by Circumventing Text Feature Learning

ICLR 2024Poster
5.8
4

Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line

NeurIPS 2024Poster
6.5
4

Predicting the Performance of Foundation Models via Agreement-on-the-Line

NeurIPS 2024Poster
5.8
4

Predicting the Performance of Foundation Models via Agreement-on-the-line

ICLR 2024Rejected
5.8
5

Rethinking LLM Memorization through the Lens of Adversarial Compression

NeurIPS 2024Poster
6.5
4

TOFU: A Task of Fictitious Unlearning for LLMs

COLM 2024Poster
4.3
4

The Update-Equivalence Framework for Decision-Time Planning

ICLR 2024Poster
4.7
3

Computing Low-Entropy Couplings for Large-Support Distributions

ICLR 2024Rejected
6.4
5

Improving Alignment and Robustness with Circuit Breakers

NeurIPS 2024Poster
6.5
4

Manifold Preserving Guided Diffusion

ICLR 2024Poster
5.3
4

Robustness Evaluation of Proxy Models against Adversarial Optimization

ICLR 2024Rejected
5.7
3

Enhancing Neural Network Transparency through Representation Analysis

ICLR 2024Rejected