PaperHub

Bernhard Schölkopf

~Bernhard_Schölkopf1

39
论文总数
19.5
年均投稿
6.3
平均评分
接收情况32/39
会议分布
ICLR
22
NeurIPS
12
ICML
3
COLM
2

发表论文 (39 篇)

202520

6.8
5

Preference Elicitation for Offline Reinforcement Learning

ICLR 2025Poster
6.8
4

SPARTAN: A Sparse Transformer World Model Attending to What Matters

NeurIPS 2025Poster
5.5
4

Direct Advantage Estimation in Partially Observable Environments

ICLR 2025Rejected
6.4
4

Counterfactual reasoning: an analysis of in-context emergence

NeurIPS 2025Poster
6.3
4

Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy Filtering

ICLR 2025Poster
4.4
5

Verbalized Machine Learning: Revisiting Machine Learning with Language Models

ICLR 2025withdrawn
5.5
4

Learning Joint Interventional Effects from Single-Variable Interventions in Additive Models

ICML 2025Poster
7.0
4

MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs

ICLR 2025Poster
7.0
5

Standardizing Structural Causal Models

ICLR 2025Poster
6.5
6

Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning

ICLR 2025Spotlight
6.8
4

The Directionality of Optimization Trajectories in Neural Networks

ICLR 2025Poster
5.5
4

Generative Intervention Models for Causal Perturbation Modeling

ICML 2025Poster
7.0
3

Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Games

COLM 2025Poster
7.3
4

Reparameterized LLM Training via Orthogonal Equivalence Transformation

NeurIPS 2025Poster
5.5
3

Generalized Interpolating Discrete Diffusion

ICML 2025Poster
7.8
4

Do-PFN: In-Context Learning for Causal Effect Estimation

NeurIPS 2025Spotlight
6.8
4

Flipping Against All Odds: Reducing LLM Coin Flip Bias via Verbalized Rejection Sampling

NeurIPS 2025Rejected
6.8
4

Are Language Models Efficient Reasoners? A Perspective from Logic Programming

NeurIPS 2025Poster
7.3
3

Can Large Language Models Understand Symbolic Graphics Programs?

ICLR 2025Spotlight
7.3
4

Language Model Alignment in Multilingual Trolley Problems

ICLR 2025Spotlight

202419

6.3
4

Skill or Luck? Return Decomposition via Advantage Functions

ICLR 2024Poster
7.5
4

Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding

ICLR 2024Poster
6.8
4

Out-of-Variable Generalisation for Discriminative Models

ICLR 2024Poster
5.5
4

Causal vs. Anticausal merging of predictors

NeurIPS 2024Poster
5.0
5

Deep Backtracking Counterfactuals for Causally Compliant Explanations

ICLR 2024Rejected
-

Moûsai: Efficient Text-to-Music Diffusion Models

ICLR 2024withdrawn
6.3
4

From Causal to Concept-Based Representation Learning

NeurIPS 2024Poster
5.8
4

Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents

NeurIPS 2024Poster
6.8
4

The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks.

ICLR 2024Poster
5.3
4

Limits of Transformer Language Models on Learning to Compose Algorithms

NeurIPS 2024Poster
7.3
3

Do Finetti: On Causal Effects for Exchangeable Data

NeurIPS 2024Oral
6.5
4

Identifying Policy Gradient Subspaces

ICLR 2024Poster
5.8
4

Redesigning Information Markets in the Era of Language Models

COLM 2024Poster
5.5
4

Rethinking the Buyer’s Inspection Paradox in Information Markets with Language Agents

ICLR 2024Rejected
7.3
4

Ghost on the Shell: An Expressive Representation of General 3D Shapes

ICLR 2024Oral
6.0
3

Can Large Language Models Infer Causation from Correlation?

ICLR 2024Poster
3.0
3

Causal Impact Index: A Causal Formulation of Citations

ICLR 2024withdrawn
5.5
4

On Affine Homotopy between Language Encoders

NeurIPS 2024Poster
6.3
3

Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization

ICLR 2024Poster