TMLR Published Papers
LightNews LightNews
banner
tmlr-pub.bsky.social
TMLR Published Papers
@tmlr-pub.bsky.social
550 followers 1 following 1.6K posts
TMLR Homepage: https://jmlr.org/tmlr/
TMLR Infinite Conference: https://tmlr.infinite-conf.org/
Posts Replies Media Videos
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

Pref-GUIDE: Continual Policy Learning from Real-Time Human Feedback via Preference-Based Learning

Zhengran Ji, Boyuan Chen

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

#reward #rewards #reinforcement
Pref-GUIDE: Continual Policy Learning from Real-Time Human Feedback via Preference-Based Learning
October 19, 2025 at 8:29 PM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

AB-UPT: Scaling Neural CFD Surrogates for High- Fidelity Automotive Aerodynamics Simulations via Anc...

Benedikt Alkin, Maurits Bleeker, Richard Kurle et al.

https://tmlr.infinite-conf.org/paper_pages/nwQ8nitlTZ

#aerodynamics #meshing #cfd
AB-UPT: Scaling Neural CFD Surrogates for High- Fidelity Automotive Aerodynamics Simulations via Anc...
October 19, 2025 at 4:29 PM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

Teaching Diffusion Models to Ground Alpha Matte

Tianyi Xiang, Weiying Zheng, Yutao Jiang et al.

https://tmlr.infinite-conf.org/paper_pages/2gNy9Yeg8J

#matting #matte #transparency
Teaching Diffusion Models to Ground Alpha Matte
October 19, 2025 at 12:29 PM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

Exponential Scaling of Factual Inconsistency in Data-to-Text Generation with Fine-Tuned LLMs

Joy Mahapatra, Soumyajit Roy, Utpal Garain

https://tmlr.infinite-conf.org/paper_pages/xPaPd6g5WG

#scaling #scale #inconsistencies
Exponential Scaling of Factual Inconsistency in Data-to-Text Generation with Fine-Tuned LLMs
October 19, 2025 at 8:29 AM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

Data-Driven Discovery of PDEs via the Adjoint Method

Mohsen Sadr, Tony Tohme, KAMAL YOUCEF-TOUMI

https://tmlr.infinite-conf.org/paper_pages/Az3mJ4d1eT

#pdes #pde #gradients
Data-Driven Discovery of PDEs via the Adjoint Method
October 19, 2025 at 4:29 AM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

Learning Reward Machines from Partially Observed Policies

Mohamad Louai Shehab, Antoine Aspeel, Necmiye Ozay

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

#reinforcement #reward #markov
Learning Reward Machines from Partially Observed Policies
October 19, 2025 at 12:29 AM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

VSCoDe: Visual-Augmentation Selection for Contrastive Decoding

Sihyeon Kim, Boryeong Cho, Sangmin Bae, Sumyeong Ahn, Se-Young Yun

https://tmlr.infinite-conf.org/paper_pages/CqSyPc9W7Y

#visual #contrasts #contrast
VSCoDe: Visual-Augmentation Selection for Contrastive Decoding
October 18, 2025 at 8:29 PM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

Simplifying Knowledge Transfer in Pretrained Models

Siddharth Jain, Shyamgopal Karthik, Vineet Gandhi

https://tmlr.infinite-conf.org/paper_pages/eQ9AVtDaP3

#saliency #learning #deep
Simplifying Knowledge Transfer in Pretrained Models
October 13, 2025 at 8:31 PM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

Uncertainty Quantification in Retrieval Augmented Question Answering

Laura Perez-Beltrachini, Mirella Lapata

https://tmlr.infinite-conf.org/paper_pages/JLkgI0h7wy

#retrieval #answering #qa
Uncertainty Quantification in Retrieval Augmented Question Answering
October 13, 2025 at 4:32 PM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

Continuous Language Model Interpolation yields Dynamic and Controllable Text Generation

Sara Kangaslahti, David Alvarez-Melis

https://tmlr.infinite-conf.org/paper_pages/xD9Nu2Wah4

#adapting #models #interpolation
Continuous Language Model Interpolation yields Dynamic and Controllable Text Generation
October 13, 2025 at 12:31 PM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

Enhancing Cost Efficiency in Active Learning with Candidate Set Query

Yeho Gwon, Sehyun Hwang, Hoyoung Kim, Jungseul Ok, Suha Kwak

https://tmlr.infinite-conf.org/paper_pages/LhHxl30xQ1

#classification #labeling #learning
Enhancing Cost Efficiency in Active Learning with Candidate Set Query
October 13, 2025 at 8:30 AM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

Solution Augmentation for ARC Problems Using GFlowNet: A Probabilistic Exploration Approach

Sanha Hwang, Seungpil Lee, Sejin Kim, Sundong Kim

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

#generative #abstraction #gflownet
Solution Augmentation for ARC Problems Using GFlowNet: A Probabilistic Exploration Approach
October 13, 2025 at 4:30 AM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

Identifying Macro Causal Effects in a C-DMG over ADMGs

Simon Ferreira, Charles K. Assaad

https://tmlr.infinite-conf.org/paper_pages/905LEugq6R

#causal #graphs #clusters
Identifying Macro Causal Effects in a C-DMG over ADMGs
October 13, 2025 at 12:31 AM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

LAPP: Large Language Model Feedback for Preference-Driven Reinforcement Learning

Pingcheng Jian, Xiao Wei, Yanbaihui Liu, Samuel A. Moore, Michael M. Zavlanos, Boyuan Chen

https://tmlr.infinite-conf.org/paper_pages/cq76wx7T9F

#reinforcement #robot
LAPP: Large Language Model Feedback for Preference-Driven Reinforcement Learning
October 12, 2025 at 8:30 PM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

Variance Reduced Smoothed Functional REINFORCE Policy Gradient Algorithms

Shalabh Bhatnagar, Deepak H R

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

#reinforce #optimization #gradient
Variance Reduced Smoothed Functional REINFORCE Policy Gradient Algorithms
October 12, 2025 at 4:30 PM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

GROOD: GRadient-Aware Out-of-Distribution Detection

Mostafa ElAraby, Sabyasachi Sahoo, Yann Pequignot, Paul Novello, Liam Paull

https://tmlr.infinite-conf.org/paper_pages/2V7itvvMVJ

#neural #imagenet #gradients
GROOD: GRadient-Aware Out-of-Distribution Detection
October 12, 2025 at 12:30 PM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

Communication Cost Reduction for Subgraph Counting under Local Differential Privacy via Hash Functio...

Quentin Hillebrand, Vorapong Suppakitpaisarn, Tetsuo Shibuya

https://tmlr.infinite-conf.org/paper_pages/N1J236mepp

#hashing #privacy #subgraph
Communication Cost Reduction for Subgraph Counting under Local Differential Privacy via Hash Functio...
October 12, 2025 at 8:30 AM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

Loss Landscape Degeneracy and Stagewise Development in Transformers

Jesse Hoogland, George Wang, Matthew Farrugia-Roberts et al.

https://tmlr.infinite-conf.org/paper_pages/45qJyBG8Oj

#neural #transformers #learning
Loss Landscape Degeneracy and Stagewise Development in Transformers
October 12, 2025 at 4:30 AM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

A note on the $k$-means clustering for missing data

Yoshikazu Terada, Xin Guan

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

#cluster #clustering #minimized
A note on the $k$-means clustering for missing data
October 12, 2025 at 12:30 AM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors

Soumava Paul, Prakhar Kaushik, Alan Yuille

https://tmlr.infinite-conf.org/paper_pages/yp1CYo6R0r

#camera #scenes #pose
Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors
October 11, 2025 at 8:30 PM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

ASkDAgger: Active Skill-level Data Aggregation for Interactive Imitation Learning

Jelle Luijkx, Zlatan Ajanović, Laura Ferranti, Jens Kober

https://tmlr.infinite-conf.org/paper_pages/987Az9f8fT

#novice #interactive #askdagger
ASkDAgger: Active Skill-level Data Aggregation for Interactive Imitation Learning
October 11, 2025 at 4:30 PM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

Hallucination Detection on a Budget: Efficient Bayesian Estimation of Semantic Entropy

Kamil Ciosek, Nicolò Felicioni, Sina Ghiassian

https://tmlr.infinite-conf.org/paper_pages/j2N2RuNdbC

#hallucination #entropy #semantic
Hallucination Detection on a Budget: Efficient Bayesian Estimation of Semantic Entropy
October 11, 2025 at 12:31 PM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

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

Lukas Gosch, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar, Stephan Günnemann

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

#adversarial #networks
Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks
October 11, 2025 at 8:31 AM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

Compressed Decentralized Momentum Stochastic Gradient Methods for Nonconvex Optimization

Wei Liu, Anweshit Panda, Ujwal Pandey et al.

https://tmlr.infinite-conf.org/paper_pages/RqhMQHHkB4

#compression #compressed #nonconvex
Compressed Decentralized Momentum Stochastic Gradient Methods for Nonconvex Optimization
October 11, 2025 at 4:31 AM
tmlr-pub.bsky.social
New #TMLR-Paper-with-Video:

LumiNet: Perception-Driven Knowledge Distillation via Statistical Logit Calibration

Md. Ismail Hossain, M M Lutfe Elahi, Sameera Ramasinghe et al.

https://tmlr.infinite-conf.org/paper_pages/3rU1lp9w2l

#distillation #distill #knowledge
LumiNet: Perception-Driven Knowledge Distillation via Statistical Logit Calibration
October 11, 2025 at 12:30 AM