New #J2C Certification:
Process Reward Models That Think
Muhammad Khalifa, Rishabh Agarwal, Lajanugen Logeswaran et al.
https://openreview.net/forum?id=FPVCb0WMuN
#thinkprm #reward #trained
Nonlinear reconciliation: Error reduction theorems
Lorenzo Nespoli, Anubhab Biswas, Roberto Rocchetta, Vasco Medici
Action editor: Samuel Vaiter
https://openreview.net/forum?id=dXRWuogm3J
#hypersurfaces #manifolds #curvature
New #Survey Certification:
A Survey of Reasoning in Autonomous Driving Systems: Open Challenges and Emerging Paradigms
Kejin Yu, Yuhan Sun, Taiqiang Wu et al.
https://openreview.net/forum?id=XwQ7dc4bqn
#driving #autonomous #cognitive
Supervised score aggregation for active anomaly detection
Kevin Bleakley, Martin Royer, Benjamin Auder
Action editor: Philip Chan
https://openreview.net/forum?id=nrmJD3XMA3
#anomaly #anomalies #classifier
New #J2C Certification:
Mollifier Layers: Enabling Efficient High-Order Derivatives in Inverse PDE Learning
Vinayak Vinayak, Ananyae Kumar bhartari, Vivek Shenoy
https://openreview.net/forum?id=6mFVZSzyev
#derivatives #mollifiers #differential
ASMa: Asymmetric Spatio-temporal Masking for Skeleton Action Representation Learning
Aman Anand, Amir Eskandari, Elyas Rashno, Farhana Zulkernine
Action editor: Jianbo Jiao
https://openreview.net/forum?id=kIFo1q3VMS
#skeleton #recognition #representations
BenchOverflow: Measuring Overflow in Large Language Models via Plain-Text Prompts
Erin Feiglin, Nir Hutnik, Raz Lapid
Action editor: Lingpeng Kong
https://openreview.net/forum?id=tiQjg5i4ii
#benchoverflow #overflow #prompts
PRISM: Diversifying Dataset Distillation by Decoupling Architectural Priors
Brian Bernhard Moser, Shalini Sarode, Federico Raue et al.
Action editor: Jaesik Park
https://openreview.net/forum?id=xN58FtB1Gq
#normalization #regularization #batch
On a Gradient Approach to Chebyshev Center Problems with Applications to Function Learning
Abhinav Raghuvanshi, Mayank Baranwal, Debasish Chatterjee
Action editor: Zhiyu Zhang
https://openreview.net/forum?id=lPZVsDhyj3
#optimization #optimal #gradient
SiLVR: A Simple Language-based Video Reasoning Framework
Ce Zhang, Yan-Bo Lin, Ziyang Wang, Mohit Bansal, Gedas Bertasius
Action editor: Anurag Arnab
https://openreview.net/forum?id=mQZbh9Zlbw
#multimodal #subtitles #captions
Beyond Affinity: A Benchmark of 1D, 2D, and 3D Methods Reveals Critical Trade-offs in Structure-B...
Kangyu Zheng, Kai Zhang, Jiale Tan et al.
Action editor: Markus Heinonen
https://openreview.net/forum?id=gaTwx1rzCw
#ligand #docking #pharmaceutical
New #Expert Certification:
Learning Lagrangian Interaction Dynamics with Sampling-Based Model Order Reduction
Hrishikesh Viswanath, Yue Chang, Aleksey Panas et al.
https://openreview.net/forum?id=vXCQA1EzaG
#lagrangian #fluids #sampling
One-Sided Matrix Completion from Ultra-Sparse Samples
Hongyang R. Zhang, Zhenshuo Zhang, Huy Nguyen, Guanghui Lan
Action editor: Ruoyu Sun
https://openreview.net/forum?id=vYGi4Dj777
#sparse #imputation #missingness
New #Survey Certification:
Open Technical Problems in Open-Weight AI Model Risk Management
Stephen Casper, Kyle O'Brien, Shayne Longpre et al.
https://openreview.net/forum?id=8QyGLnFkzc
#risks #weights #risk
AC-PKAN: Attention-Enhanced and Chebyshev Polynomial-Based Physics-Informed Kolmogorov–Arnold Net...
Hangwei Zhang, Zhimu Huang, Yan Wang
Action editor: Nicolas THOME
https://openreview.net/forum?id=J4SkwpIgj7
#attention #chebyshev1kans #gradient
New #J2C Certification:
Continual Robot Learning via Language-Guided Skill Acquisition
Shuo Cheng, Zhaoyi Li, Kelin Yu, Danfei Xu
https://openreview.net/forum?id=oYRNxxGN9u
#reinforcement #skills #skill
COLT: Enhancing Video Large Language Models with Continual Tool Usage
Yuyang Liu, Meng Cao, Xinyuan Shi, Xiaodan Liang
Action editor: Yuhang Zang
https://openreview.net/forum?id=NT9tHHTlXn
#videotoolbench #tools #tool
New #Survey Certification:
From Euclidean to Graph-Structured Data: A Survey of Collaborative Learning
Rémi Bourgerie, Sarunas Girdzijauskas, Viktoria Fodor
https://openreview.net/forum?id=vj9l8AjLT6
#graphs #privacy #collaborative
Quantifying Context Bias in Domain Adaptation for Object Detection
Hojun Son, Asma A. Almutairi, Arpan Kusari
Action editor: Xuming He
https://openreview.net/forum?id=YRU0A0nraG
#detection #adaptation #training
New #Featured Certification, #J2C Certification:
Discovering Symbolic Differential Equations with Symmetry Invariants
Jianke Yang, Manu Bhat, Bryan Hu, Yadi Cao, Nima Dehmamy, Robin Walters, Rose Yu
https://openreview.net/forum?id=9t1dEyYfPc
#symmetry #discovering #invariants
Calibration Enhanced Decision Maker: Towards Trustworthy Sequential Decision-Making with Large Se...
Haoyuan Sun, Bo Xia, Yifu Luo, Tiantian Zhang, Xueqian Wang
Action editor: Shaofeng Zou
https://openreview.net/forum?id=b6WcxPEb48
#reinforcement #agent #models
New #J2C Certification:
StethoLM: Audio Language Model for Cardiopulmonary Analysis Across Clinical Tasks
Yishan Wang, Tsai-Ning Wang, Mathias Funk, Aaqib Saeed
https://openreview.net/forum?id=i9RuUH9Jyj
#audio #cardiopulmonary #recordings
Symmetry in Neural Network Parameter Spaces
Bo Zhao, Robin Walters, Rose Yu
Action editor: Jeffrey Pennington
https://openreview.net/forum?id=jLpWq5QY6I
#symmetry #symmetries #deep
New #J2C Certification:
Prompt Estimation from Prototypes for Federated Prompt Tuning of Vision Transformers
M Yashwanth, Sharannya Ghosh, Aditay Tripathi, Anirban Chakraborty
https://openreview.net/forum?id=gO1CpPRj6A
#prompts #prompt #contextualized
Consistency Trajectory Planning: High-Quality and Efficient Trajectory Optimization for Offline M...
Guanquan Wang, Takuya Hiraoka, Yoshimasa Tsuruoka
Action editor: Matteo Papini
https://openreview.net/forum?id=RVGkT9ISVf
#planning #reinforcement #trajectory
New #J2C Certification:
Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federat...
Raghav Singhal, Kaustubh Ponkshe, Rohit Vartak, Lav R. Varshney, Praneeth Vepakomma
https://openreview.net/forum?id=87UyFEhzyP
#llms #lora #scalable
Estimating Expected Calibration Error for Positive-Unlabeled Learning
Ryuichi Kiryo, Futoshi Futami, Masashi Sugiyama
Action editor: Bruno Loureiro
https://openreview.net/forum?id=SvoBtLIrPZ
#classifiers #classifier #supervised
New #Featured Certification:
Learning to reconstruct from saturated data: audio declipping and high-dynamic range imaging
Victor Sechaud, Laurent Jacques, Patrice Abry, Julián Tachella
https://openreview.net/forum?id=AkJWgglkLd
#reconstruct #inverse #imaging
DeepSeek-R1 Thoughtology: Let’s think about LLM reasoning
Sara Vera Marjanovic, Arkil Patel, Vaibhav Adlakha et al.
Action editor: Mohammad Emtiyaz Khan
https://openreview.net/forum?id=BZwKsiRnJI
#thinking #reasoning #thoughtology
New #Featured Certification:
GIFT: A Framework Towards Global Interpretable Faithful Textual Explanations of Vision Classifiers
Eloi Zablocki, Valentin Gerard, Amaia Cardiel, Eric Gaussier, Matthieu Cord, Eduardo Valle
https://openreview.net/forum?id=OwhW5MpFmD
#saliency #visual
