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

New #TMLR-Paper-with-Video:

DeGLIF for Label Noise Robust Node Classification using GNNs

Pintu Kumar, Nandyala Hemachandra

https://tmlr.infinite-conf.org/paper_pages/pcs5DmBtUJ

#graph #networks #denoising

New #TMLR-Paper-with-Video:

Protein structural superfamily classification using hand-crafted and language model features: A perf...

Pranav Machingal, Rakesh Busi, Nandyala Hemachandra, Petety V. Balaji

https://tmlr.infinite-conf.org/paper_pages/huTeyYU0yD

#classifiers #classifying

New #TMLR-Paper-with-Video:

Attention-Head Binding as a Term-Conditioned Mechanistic Marker of Accessibility Concept Emergence i...

Khanh-Dung Tran

https://tmlr.infinite-conf.org/paper_pages/QG7mfCy9mu

#accessibility #attention #language

New #TMLR-Paper-with-Video:

Imitating What Works: Simulation-Filtered Modular Policy Learning from Human Videos

Albert J. Zhai, Kuo-Hao Zeng, Jiasen Lu, Ali Farhadi, Shenlong Wang, Wei-Chiu Ma

https://tmlr.infinite-conf.org/paper_pages/ZEmv4DhaGL

#grasping #grasp #grasps

New #TMLR-Paper-with-Video:

FedPS: Federated Preprocessing for structured data via aggregated Statistics

Xuefeng Xu, Graham Cormode

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

#aggregated #federated #datasets

New #TMLR-Paper-with-Video:

LoraQuant: Mixed-Precision Quantization of LoRA to Ultra- Low Bits for LLM Customization

Amir Reza Mirzaei, Yuqiao Wen, Yanshuai Cao, Lili Mou

https://tmlr.infinite-conf.org/paper_pages/71svCWi178

#quantization #quantizing #quantize

New #TMLR-Paper-with-Video:

Harnessing Heterogeneity: Improving Convergence Through Partial Variance Control in Federated Learni...

Pranab Sahoo, Ashutosh Tripathi, Sriparna Saha, Samrat Mondal

https://tmlr.infinite-conf.org/paper_pages/I9VhJ5iLNr

#learning #collaborative #federated

New #TMLR-Paper-with-Video:

Disentangling Intrinsic Importance from Emergent Structure in Multi-Expert Orchestration

Sudipto Ghosh, Sujoy Nath, Sunny Manchanda, Tanmoy Chakraborty

https://tmlr.infinite-conf.org/paper_pages/4W7sgat04A

#orchestrator #orchestration #deepseek

New #TMLR-Paper-with-Video:

Universal Latent Homeomorphic Manifolds: A Framework for Cross-Domain Representation Unification

Tong Wu, Tayab Uddin Wara, Daniel Hernandez, Sidong Lei

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

#homeomorphic #manifold #manifolds

New #TMLR-Paper-with-Video:

Savaal: Scalable Concept-Driven Question Generation to Enhance Human Learning

Kimia Noorbakhsh, Joseph Chandler, Pantea Karimi, Mohammad Alizadeh, Hari Balakrishnan

https://tmlr.infinite-conf.org/paper_pages/2DWDQTsz7K

#questions #answering #learning

New #TMLR-Paper-with-Video:

FreeEyeglass: Training-free and Target-mask-free Eyeglass Transfer for Facial Videos

Weng Ian Chan, Yuantian Huang, Xingchao Yang, Fumio Okura, Takafumi Taketomi

https://tmlr.infinite-conf.org/paper_pages/6aFRoQcm3H

#autoencoders #autoencoder #inpainting

New #TMLR-Paper-with-Video:

The Hidden Cost of Modeling P(x): Vulnerability to Membership Inference Attacks in Generative Text C...

Owais Makroo, Siva Rajesh Kasa, Sumegh Roychowdhury et al.

https://tmlr.infinite-conf.org/paper_pages/SHMC01wdVM

#privacy #classifiers #generative

New #TMLR-Paper-with-Video:

Learning-Augmented Robust Algorithmic Recourse

Kshitij Kayastha, Vasilis Gkatzelis, Shahin Jabbari

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

#adversarial #robustness #recourses

New #TMLR-Paper-with-Video:

Augmented Mixup Procedure for Privacy-Preserving Collaborative Training

Mihail-Iulian Pleșa, Fabrice Clérot, Simona Elena David, Robert Poenaru

https://tmlr.infinite-conf.org/paper_pages/1SrZyNgmpY

#privacy #imagenet #obfuscation

Sakana AI’s LLM Peer Review System Catches 73% of Core-Claim Errors #Technology #AI #AIResearch #sakanaai #llmreview #peerreview #tmlr #errorcorrection

https://puretech.news/read?id=234839614525800448

New #TMLR-Paper-with-Video:

Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learning

Yuheng Lei, Sitong Mao, Shunbo Zhou, Hongyuan Zhang, Xuelong Li, Ping Luo

https://tmlr.infinite-conf.org/paper_pages/MHVBrjS8cG

#lifelong #forgetting #robot

New #TMLR-Paper-with-Video:

CodecSep: Prompt-Driven Universal Sound Separation on Neural Audio Codec Latents

Adhiraj Banerjee, Vipul Arora

https://tmlr.infinite-conf.org/paper_pages/r63GX9hKhC

#audiosep #audio #codecsep

New #TMLR-Paper-with-Video:

Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic

Siqi Zeng, Yifei He, Meitong Liu et al.

https://tmlr.infinite-conf.org/paper_pages/zkc7u3mIaE

#basis #bases #tasks