PaperHub
影响力指数
89.74/100
前 0.6%
全站排名 #387
发表论文30 篇
平均评分5.3
年均产出10.0 篇/年

Elias Stengel-Eskin

Assistant Professor@University of Texas at Austin·美国·OpenReview
研究方向

Ambiguity · Uncertainty and Calibration · Multimodal NLP · Grounded Language · Semantic Parsing · Natural Language Processing

5.5
12

PoSh: Using Scene Graphs to Guide LLMs-as-a-Judge for Detailed Image Descriptions

ICLR 2026Poster
二作
5.5
21

Gistify: Codebase-Level Understanding via Runtime Execution

ICLR 2026Poster
5.0
27

The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration

ICLR 2026Rejected
二作
5.0
19

Calibrating Verbalized Confidence with Self-Generated Distractors

ICLR 2026Poster
二作
5.0
21

UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning

ICLR 2026Rejected
二作
5.0
20

CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval

ICLR 2026Rejected
三作
4.8
25

Movie Facts and Fibs (MF$^2$): A Benchmark for Long Movie Understanding

ICLR 2026Rejected
4.7
21

One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration

ICLR 2026Poster
三作
4.7
25

TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models

ICLR 2026Poster
4.5
14

Proof-Verifier: Enabling Reinforcement Learning from Verifiable Rewards for Mathematical Theorem Proving

ICLR 2026Rejected
4.4
23

Executable Functional Abstractions: Inferring Generative Programs for Advanced Math Problems

ICLR 2026Rejected
二作
4.0
26

Symbolic Mixture-of-Experts: Adaptive Skill-based Routing for Heterogeneous Reasoning

ICLR 2026Rejected
三作
4.0
15

Self-Knowledge Without a Self? Learning Calibrated and Model-Agnostic Correctness Predictors from Historical Patterns

ICLR 2026Rejected
3.5
20

Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression

ICLR 2026Rejected
3.0
16

How Should We Evaluate LLM Reasoning Quality For Fact Verification?

ICLR 2026Rejected
7.5
24

DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback

ICLR 2025Spotlight
二作
7.0
15

Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for Compression

COLM 2025Poster
三作
7.0
17

LASeR: Learning to Adaptively Select Reward Models with Multi-Arm Bandits

NeurIPS 2025Poster
三作
6.3
23

Retrieval-Augmented Generation with Conflicting Evidence

COLM 2025Poster
三作
6.0
20

See It from My Perspective: How Language Affects Cultural Bias in Image Understanding

ICLR 2025Poster
二作
5.7
18

Learning to Generate Unit Tests for Automated Debugging

COLM 2025Poster
二作
5.7
25

GenerationPrograms: Fine-grained Attribution with Executable Programs

COLM 2025Poster
三作
5.3
31

LASeR: Learning to Adaptively Select Reward Models with Multi-Armed Bandits

ICLR 2025Rejected
三作
4.8
35

MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning

ICLR 2025Rejected
4.6
6

VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos

ICLR 2025Withdrawn
三作
3.8
17

System 1.x: Learning to Balance Fast and Slow Planning with Language Models

ICLR 2025Poster
合作者 (20)