PaperHub
影响力指数
91.44/100
前 0.5%
全站排名 #305
发表论文34 篇
平均评分5.1
年均产出11.3 篇/年

Thomas L. Griffiths

Professor@Princeton University·美国·OpenReview
研究方向

Cognitive science · Computational models of cognition · Nonparametric Bayes · Topic models · Computational social science

6.0
13

Demystifying The Mechanisms Behind Emergent Exploration in Goal-Conditioned RL

ICLR 2026Poster
5.3
14

An evolutionary perspective on modes of learning in Transformers

ICLR 2026Poster
二作
5.0
19

Toward Efficient Exploration by Large Language Model Agents

ICLR 2026Poster
二作
4.7
17

Large Language Models Develop Novel Social Biases Through Adaptive Exploration

ICLR 2026Rejected
通讯
4.5
19

Assessing the Reverse-Engineering Abilities of Large Language Models

ICLR 2026Rejected
通讯
4.5
17

Using Reinforcement Learning to Train Large Language Models to Explain Human Decisions

ICLR 2026Poster
通讯
4.5
13

Visual serial processing deficits explain divergences in human and VLM reasoning

ICLR 2026Desk Rejected
通讯
4.0
13

Steering Risk Preferences in Large Language Models by Aligning Behavioral and Neural Representations

ICLR 2026Rejected
三作
4.0
21

Localized Cultural Knowledge is Conserved and Controllable in Large Language Models

ICLR 2026Withdrawn
4.0
25

Evaluating Language Models' Evaluations of Games

ICLR 2026Poster
通讯
3.5
14

Learning is Forgetting; LLM Training As Lossy Compression

ICLR 2026Poster
3.5
12

Accumulating Context Changes the Beliefs of Language Models

ICLR 2026Rejected
通讯
3.0
11

VideoGameBench: Can Vision-Language Models complete popular video games?

ICLR 2026Desk Rejected
二作
2.5
6

Automating Meta-learning by Learning to Map Task Distributions to Initial Weights

ICLR 2026Rejected
二作
2.0
11

Amortized Bayesian Meta-Learning for Low-Rank Adaptation of Large Language Models

ICLR 2026Rejected
三作
7.8
11

Conformal Prediction as Bayesian Quadrature

ICML 2025Oral
二作
7.3
18

Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)

NeurIPS 2025Poster
7.0
19

Language Models Trained to do Arithmetic Predict Human Risky and Intertemporal Choice

ICLR 2025Poster
三作
6.4
29

Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers

NeurIPS 2025Poster
6.4
26

Are Large Language Models Sensitive to the Motives Behind Communication?

NeurIPS 2025Poster
通讯
6.3
24

Large Language Models Assume People are More Rational than We Really are

ICLR 2025Poster
通讯
5.8
27

RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation

ICLR 2025Rejected
5.5
11

Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse

ICML 2025Poster
通讯
5.0
18

Rational Metareasoning for Large Language Models

ICLR 2025Rejected
三作
5.0
27

Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse

ICLR 2025Rejected
通讯
4.0
6

Using Contrastive Learning with Generative Similarity to Learn Spaces that Capture Human Inductive Biases

ICLR 2025Withdrawn
通讯
合作者 (20)