Lightnews — Scholar-powered news

TMLR Published Papers @tmlr-pub.bsky.social · 10m

Cross-lingual Transfer in Programming Languages: An Extensive Empirical Study

Razan Baltaji, Saurabh Pujar, Martin Hirzel, Louis Mandel, Luca Buratti, Lav R. Varshney

Action editor: Hugo Touvron

https://openreview.net/forum?id=1PRBHKgQVM

#languages #programming #language

TMLR Published Papers @tmlr-pub.bsky.social · 3h

New #TMLR-Paper-with-Video:

Overcoming Knowledge Barriers: Online Imitation Learning from Visual Observation with Pretrained Wor...

Xingyuan Zhang, Philip Becker-Ehmck, Patrick van der Smagt, Maximilian Karl

https://tmlr.infinite-conf.org/paper_pages/BaRD2Nfj41

#imitation #deepmind

1

TMLR Published Papers @tmlr-pub.bsky.social · 4h

Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey

Atsuyuki Miyai, Jingkang Yang, Jingyang Zhang et al.

Action editor: Chuan Sheng Foo

https://openreview.net/forum?id=FO3IA4lUEY

#detection #detecting #recognition

2

TMLR Published Papers @tmlr-pub.bsky.social · 7h

New #TMLR-Paper-with-Video:

Change Point Detection in Dynamic Graphs with Decoder-only Latent Space Model

Yik Lun Kei, Jialiang Li, Hangjian Li, Yanzhen Chen, OSCAR HERNAN MADRID PADILLA

https://tmlr.infinite-conf.org/paper_pages/DVeFqV56Iz

#lasso #regularization #graphs

TMLR Published Papers @tmlr-pub.bsky.social · 8h

GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation

Quankai Gao, Qiangeng Xu, Zhe Cao et al.

Action editor: David Fouhey

https://openreview.net/forum?id=XBL7xi5rt0

#gaussianflow #4d #flow

TMLR Published Papers @tmlr-pub.bsky.social · 11h

New #TMLR-Paper-with-Video:

Selective Concept Bottleneck Models Without Predefined Concepts

Simon Schrodi, Julian Schur, Max Argus, Thomas Brox

https://tmlr.infinite-conf.org/paper_pages/PMO30TLI4l

#bottleneck #concepts #classification

1

TMLR Published Papers @tmlr-pub.bsky.social · 12h

Reassessing Fairness: A Reproducibility Study of NIFA’s Impact on GNN Models

Ruben Figge, Sjoerd Gunneweg, Aaron Kuin, Mees Lindeman

Action editor: Sheng Li

https://openreview.net/forum?id=l5fXUKi8GO

#fairness #biases #gnn

1

TMLR Published Papers @tmlr-pub.bsky.social · 15h

New #TMLR-Paper-with-Video:

Text to Stealthy Adversarial Face Masks

Ben Lewis, Thomas Moyse, James Parkinson, Elizabeth Telford, Callum Whitfield, Ranko Lazic

https://tmlr.infinite-conf.org/paper_pages/XYqCx026AI

#adversarial #stealthy #stealthiness

TMLR Published Papers @tmlr-pub.bsky.social · 16h

A Survey on Verifiable Cross-Silo Federated Learning

Aleksei Korneev, Jan Ramon

Action editor: Antti Koskela

https://openreview.net/forum?id=uMir8UIHST

#verifiable #federated #privacy

TMLR Published Papers @tmlr-pub.bsky.social · 19h

New #TMLR-Paper-with-Video:

Connecting Parameter Magnitudes and Hessian Eigenspaces at Scale using Sketched Methods

Andres Fernandez, Frank Schneider, Maren Mahsereci, Philipp Hennig

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

#hessians #hessian #grassmannian

4

TMLR Published Papers @tmlr-pub.bsky.social · 20h

[Re] Benchmarking LLM Capabilities in Negotiation through Scoreable Games

Jorge Carrasco Pollo, Ioannis Kapetangeorgis, Joshua Rosenthal, John Hua Yao

Action editor: Quanquan Gu

https://openreview.net/forum?id=BVH81SAAh2

#negotiation #evaluations #agent

TMLR Published Papers @tmlr-pub.bsky.social · 23h

New #TMLR-Paper-with-Video:

Fairness with respect to Stereotype Predictors: Impossibilities and Best Practices

Inbal Rachel Livni Navon, Omer Reingold, Judy Hanwen Shen

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

#stereotype #fairness #stereotypes

TMLR Published Papers @tmlr-pub.bsky.social · 1d

Revisiting XRec: How Collaborative Signals Influence LLM-Based Recommendation Explanations

Cătălin-Emanuel Brița, Hieu Nguyen, Lubov Chalakova, Nikola Petrov

Action editor: Yan Liu

https://openreview.net/forum?id=cPtqOkxQqH

#recommender #attention #collaborative

TMLR Published Papers @tmlr-pub.bsky.social · 1d

New #TMLR-Paper-with-Video:

LitLLMs, LLMs for Literature Review: Are we there yet?

Shubham Agarwal, Gaurav Sahu, Abhay Puri et al.

https://tmlr.infinite-conf.org/paper_pages/heeJqQXKg7

#retrieval #keywords #literature

1 3

TMLR Published Papers @tmlr-pub.bsky.social · 1d

MagicPose4D: Crafting Articulated Models with Appearance and Motion Control

Hao Zhang, Di Chang, Fang Li, Mohammad Soleymani, Narendra Ahuja

Action editor: Ofir Lindenbaum

https://openreview.net/forum?id=qgHq1NFUJk

#articulated #poses #3d

1

TMLR Published Papers @tmlr-pub.bsky.social · 1d

New #TMLR-Paper-with-Video:

Verbalized Machine Learning: Revisiting Machine Learning with Language Models

Tim Z. Xiao, Robert Bamler, Bernhard Schölkopf, Weiyang Liu

https://tmlr.infinite-conf.org/paper_pages/k3Ab6RuJE9

#verbalized #learning #classification

2

TMLR Published Papers @tmlr-pub.bsky.social · 1d

A reproducibility study of “User-item fairness tradeoffs in recommendations”

Sander Honig, Elyanne Oey, Lisanne Wallaard, Sharanda Suttorp, Clara Rus

Action editor: Dennis Wei

https://openreview.net/forum?id=vltzxxhzLU

#fairness #recommending #preferences

TMLR Published Papers @tmlr-pub.bsky.social · 1d

New #TMLR-Paper-with-Video:

Controlled Training Data Generation with Diffusion Models

Teresa Yeo, Andrei Atanov, Harold Luc Benoit et al.

https://tmlr.infinite-conf.org/paper_pages/sSOxuUjE2o

#adversarial #generative #supervised

2

TMLR Published Papers @tmlr-pub.bsky.social · 1d

Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks

Lukas Gosch, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar, Stephan Günnemann

Action editor: Xingchen Wan

https://openreview.net/forum?id=jIAPLDdGVx

#adversarial #backdoors #robustness

1

TMLR Published Papers @tmlr-pub.bsky.social · 1d

New #TMLR-Paper-with-Video:

Lower Ricci Curvature for Efficient Community Detection

Yun Jin Park, Didong Li

https://tmlr.infinite-conf.org/paper_pages/EoiuRII7MQ

#community #networks #ricci

2

TMLR Published Papers @tmlr-pub.bsky.social · 1d

SynCode: LLM Generation with Grammar Augmentation

Shubham Ugare, Tarun Suresh, Hangoo Kang, Sasa Misailovic, Gagandeep Singh

Action editor: Ying Wei

https://openreview.net/forum?id=HiUZtgAPoH

#syntax #serialization #syntactical

TMLR Published Papers @tmlr-pub.bsky.social · 1d

New #TMLR-Paper-with-Video:

Active Diffusion Subsampling

Oisín Nolan, Tristan Stevens, Wessel L. van Nierop, Ruud Van Sloun

https://tmlr.infinite-conf.org/paper_pages/OGifiton47

#subsampling #sampling #supervised

1

TMLR Published Papers @tmlr-pub.bsky.social · 1d

Solving Multi-agent Path Finding as an LLM Benchmark: How, How Good and Why

Weizhe Chen, Sven Koenig, Bistra Dilkina

Action editor: Jiang Bian

https://openreview.net/forum?id=8hAxEFRVQT

#planning #agent #pathfinding

2

TMLR Published Papers @tmlr-pub.bsky.social · 1d

New #TMLR-Paper-with-Video:

Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics

Minttu Alakuijala, Reginald McLean, Isaac Woungang et al.

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

#robot #critic #reward

TMLR Published Papers @tmlr-pub.bsky.social · 2d

Towards Undistillable Models by Minimizing Conditional Mutual Information

Linfeng Ye, Shayan Mohajer Hamidi, EN-HUI YANG

Action editor: Hanwang Zhang

https://openreview.net/forum?id=jVABSsD4Vf

#dnn #dnns #knowledge