New #TMLR-Paper-with-Video:

Diffusion Models in Simulation-Based Inference: A Tutorial Review

Jonas Arruda, Niels Leif Bracher, Ullrich Koethe, Jan Hasenauer, Stefan T. Radev

https://tmlr.infinite-conf.org/paper_pages/86Q261z005

#modeling #models #diffusion

New #TMLR-Paper-with-Video:

Judging the Judges: A Systematic Evaluation of Bias Mitigation Strategies in LLM-as-a-Judge Pipeline...

Sadman Kabir Soumik

https://tmlr.infinite-conf.org/paper_pages/QF4lAmG4zc

#bias #biases #judges

New #TMLR-Paper-with-Video:

MEGA: Message Passing Neural Networks for Multigraphs with EdGe Attributes

H. Çağrı Bilgi, Kubilay Atasu

https://tmlr.infinite-conf.org/paper_pages/Jo4KBvnMIP

#multigraphs #networks #edge

New #TMLR-Paper-with-Video:

Training Verifiably Robust Agents Using Set-Based Reinforcement Learning

Manuel Wendl, Lukas Koller, Tobias Ladner, Matthias Althoff

https://tmlr.infinite-conf.org/paper_pages/DhRPPhSjGA

#adversarial #verifiability #robustness

New #TMLR-Paper-with-Video:

Understanding Transformer-Based Vision Models via Modular Feature Inversion

Jan Rathjens, Shirin Reyhanian, David Kappel, Laurenz Wiskott

https://tmlr.infinite-conf.org/paper_pages/O5sMv2o3EV

#transformer #deepen #deep

New #TMLR-Paper-with-Video:

Benford’s Law as a Distributional Prior for Post-Training Quantization of Large Language Models

Arthur Negrão de Faria Martins da Costa, Pedro Silva, Vander L. S. Freitas et al.

https://tmlr.infinite-conf.org/paper_pages/YiLcQY4Nje

#quantization #tensors

New #TMLR-Paper-with-Video:

On-the-go Forgetting without Explicit Unlearning via ERASE

Kushal Chakrabarti, Mayank Baranwal

https://tmlr.infinite-conf.org/paper_pages/PIXVov5LQq

#forgetting #unlearning #erase

New #TMLR-Paper-with-Video:

Semantic F1 Scores: Fair Evaluation Under Fuzzy Class Boundaries

Georgios Chochlakis, Jackson Trager, Vedant Vipul Jhaveri et al.

https://tmlr.infinite-conf.org/paper_pages/U0YJpGuFEc

#semantic #classification #fuzzy

New #TMLR-Paper-with-Video:

A Survey of Flow Matching in Reinforcement Learning

Nabuat Zaman Nahim, Fairoz Nower Khan, Peizhong Ju

https://tmlr.infinite-conf.org/paper_pages/P6e5IC4gPe

#flow #reinforcement #learning

New #TMLR-Paper-with-Video:

The Fake Mirror Effect: Foreign Feedback Disrupts Self-Correction in Minimal Recurrent Networks

Sungmoon Ong

https://tmlr.infinite-conf.org/paper_pages/cwENvGCLRv

#recurrent #feedback #mirror

New #TMLR-Paper-with-Video:

IntervalGP-VAE: Uncertainty-Aware Individual Treatment Effect Estimation via Identifiable Proxy-Base...

Zhigao Guo, Feng Dong

https://tmlr.infinite-conf.org/paper_pages/vh7cshQCAE

#confounders #confounder #unobserved

New #TMLR-Paper-with-Video:

Exposing Long-Tail Safety Failures in Large Language Models through Efficient Diverse Response Sampl...

Suvadeep Hajra, Palash Nandi, Tanmoy Chakraborty

https://tmlr.infinite-conf.org/paper_pages/tHfAskovWI

#adversarial #sampling #supervised

New #TMLR-Paper-with-Video:

XConv: Low-memory stochastic backpropagation for convolutional layers

Anirudh Thatipelli, Jeffrey J. Sam, Mathias Louboutin et al.

https://tmlr.infinite-conf.org/paper_pages/ajv7wvEvnh

#backpropagation #convolutional #neural

New #TMLR-Paper-with-Video:

Do Object Channels Improve Robustness in Deep Reinforcement Learning?

Jannis Blüml, Cedric Derstroff, Bjarne Gregori et al.

https://tmlr.infinite-conf.org/paper_pages/7BFbso4B3R

#pixels #pixel #reinforcement

New #TMLR-Paper-with-Video:

Adaptive and Stratified Subsampling for High-Dimensional Robust Estimation

Prateek Mittal, Joohi Chauhan

https://tmlr.infinite-conf.org/paper_pages/R8y19hU9Ab

#subsampling #estimation #estimators

New #TMLR-Paper-with-Video:

Extracting Common Components from Partially Observed Views Using Diffusion Geometry

Bar Weiss, Hau-Tieng Wu, Ronen Talmon

https://tmlr.infinite-conf.org/paper_pages/yTHGIV8ToF

#views #multiview #embedding

New #TMLR-Paper-with-Video:

Revisiting Neighbourhoods in Mean Field Reinforcement Learning

Sriram Ganapathi Subramanian, Matthew E. Taylor, Kate Larson, Mark Crowley, Pascal Poupart

https://tmlr.infinite-conf.org/paper_pages/PQ5R7K0WDc

#reinforcement #agents #agent

New #TMLR-Paper-with-Video:

Domain Adaptation for Cold-Start Users in Sequential Recommendation

Lu Wang, Wenyu Zhang, Wang Chengke, Guimei Liu, Ye Luo

https://tmlr.infinite-conf.org/paper_pages/jrVmW6LfMa

#embeddings #recommendation #contextual

New #TMLR-Paper-with-Video:

Freeze, Prompt, and Adapt: A Framework for Source-free Unsupervised GNN Prompting

Peyman Baghershahi, Sourav Medya

https://tmlr.infinite-conf.org/paper_pages/9KKgIQwCLO

#supervised #ugprompt #trained

New #TMLR-Paper-with-Video:

Guided Diffusion by Optimized Loss Functions on Relaxed Parameters for Inverse Material Design

Jens U. Kreber, Christian Weißenfels, Joerg Stueckler

https://tmlr.infinite-conf.org/paper_pages/JVUk7fT0Ll

#optimization #diffusion #inverse