Every paper with a summary

Every arXiv paper Paperlayer has summarized so far. Open any of them to read the summary beside the original PDF, with every point linked to the line, figure, or table it came from.

Search paper metadata (including unsummarized papers)

18,421 to 18,480 of 119,808

When is a better LLM worth paying for? Stochastic Optimization with Switching Mixed-Fidelity Oracles
Swati Gupta, Tianjiao Li
math.OCcs.AIcs.LGarXiv:2610.21139v12026
From Identification to Authentication for Micro-CSI RF Fingerprinting in OFDM Systems
Matteo Varotto, Stefano Tomasin
eess.SParXiv:2608.29845v12026
PipelineRL: Faster On-policy Reinforcement Learning for Long Sequence Generation
Alexandre Piché, Ehsan Kamalloo, Rafael Pardinas +2
cs.LGarXiv:2509.19128v22025
Graph-Theoretic Bounds for Non-Linear Function Computation Broadcast
Derya Malak, Vijith Kumar K. P., M. Reza Deylam Salehi
cs.ITmath.ITarXiv:2610.08202v12026
Variable-Granularity Tokenization for High-Resolution Object Detection
Khayrul Islam
cs.CVarXiv:2608.28706v12026
AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
Edan Toledo, Karen Hambardzumyan, Martin Josifoski +22
cs.AIcs.LGarXiv:2507.02554v22025
Compositional Information Geometry of Probabilistic Programs
Jacek Karwowski, Frank Nielsen, Sam Staton
cs.PLcs.CGarXiv:2610.17886v12026
Hard-Constrained Sampling on Embedded Riemannian Manifolds via Adjoint Schrödinger Bridges
Mattia Mosso, Jaemoo Choi, Heng Yang
eess.SYarXiv:2608.25838v12026
Entanglement-of-formation potentials for feedback-assisted classical communication and randomness distillation
Mark M. Wilde
quant-phcs.ITmath.ITarXiv:2610.04831v12026
Block encoding of semiseparable matrices via their generators
Giacomo Antonioli, Gianna M. Del Corso, Roel Van Beeumen
quant-phmath.NAarXiv:2610.13228v12026
Renormalization Group Flow Matching for Scalable Local Generative Modeling
Kanta Masuki, Yuto Ashida
cs.LGcond-mat.stat-mecharXiv:2608.23696v12026
Flexible-Antenna Systems: A Pinching-Antenna Perspective
Zhiguo Ding, Robert Schober, H. Vincent Poor
cs.ITeess.SParXiv:2412.02376v12024
Randomized Transport Maps for Model-Free Policy-Gradient Mean-Field Control
Adonis Jamal, Samy Mekkaoui, Yadh Hafsi +1
math.OCcs.LGarXiv:2610.11619v12026
Removing spurious minima for planar features by skip connections
Jakob Paul Zimmermann, Moritz Grillo, Andrei Balakin +1
cs.LGcs.AImath.OCarXiv:2610.01728v12026
The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks
Bardia Mohammadi, Lars Klein, Aman Chadha +2
cs.SEcs.LGarXiv:2608.16630v12026
Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning
Xinyang Gu, Yen-Jen Wang, Xiang Zhu +4
cs.ROcs.AIcs.SYarXiv:2408.14472v12024
SAGE: Salient Factor Discovery and Generation with Visual Foundation Representations
Shuang Liang, Lejun Liao, Shiyuan Zhang +5
cs.CVcs.LGarXiv:2609.39635v12026
Diffusion for World Modeling: Visual Details Matter in Atari
Eloi Alonso, Adam Jelley, Vincent Micheli +4
cs.LGcs.AIcs.CVarXiv:2405.12399v22024
Beyond Sequence Order: Syntax-Informed Positional Embeddings for Transformers
Haris Riaz, Hyungji Kim, Mihai Surdeanu
cs.CLcs.AIarXiv:2608.06111v12026
What Can a Gaussian Process Design Test
Ivan De Boi, Marnix Van Soom
cs.LGarXiv:2610.10122v12026
Direct Preference Optimization with an Offset
Afra Amini, Tim Vieira, Ryan Cotterell
cs.CLcs.AIcs.LGarXiv:2402.10571v22024
The Hidden Power of Scaling Factor in LoRA Optimization
Zicheng Zhang, Haoran Li, Jiaxing Wang +10
cs.AIarXiv:2606.12883v12026
Complexity separations for optimal matchgate-Clifford synthesis
Berta Casas, Diego García-Martín, Yuxuan Zhang
quant-phcs.CCarXiv:2610.06768v12026
AdaMerging: Adaptive Model Merging for Multi-Task Learning
Enneng Yang, Zhenyi Wang, Li Shen +4
cs.LGcs.CVarXiv:2310.02575v22023
Sipser-Spielman meets Dijkgraaf-Witten: non-Abelian qLDPC codes via twisted sheaf gauge theory and almost-constant-overhead magic state fountain
Guanyu Zhu, Shi Jie Samuel Tan, Ryohei Kobayashi +1
quant-phcond-mat.str-elcs.ITarXiv:2609.31541v12026
Evaluation Awareness in Language Models: Representation, Verbalization, and Control
Farzaneh Heidari, Amin Memarian, Guillaume Rabusseau
cs.CLcs.AIarXiv:2608.21766v12026
Handling plant-model mismatch in Koopman Lyapunov-based model predictive control via offset-free control framework
Sang Hwan Son, Abhinav Narasingam, Joseph Sang-Il Kwon
eess.SYcs.SYarXiv:2010.07239v12020
The Newton-Muon Optimizer
Zhehang Du, Weijie Su
math.OCcs.AIcs.LGarXiv:2604.01472v12026
The Investment Acceleration Principle Revisited by means of a Neural Network
Guido Fioretti
cs.NEarXiv:2610.03282v12026
Generative Modeling of Stochastic Dynamics for Long-Time Evolution
Yang-yang Tan, Jinyang Li, Lingxiao Wang
cond-mat.stat-mechcs.LGhep-latarXiv:2610.00546v12026
On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking
Jianliang He, Leda Wang, Siyu Chen +1
cs.LGmath.OCstat.MLarXiv:2602.16849v12026
3GPP-inspired HetNet Model using Poisson Cluster Process: Sum-product Functionals and Downlink Coverage
Chiranjib Saha, Mehrnaz Afshang, Harpreet S. Dhillon
cs.ITcs.NImath.ITarXiv:1705.01699v12017
Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models
Zhiyuan Peng, Xuyang Wu, Qifan Wang +1
cs.IRcs.AIcs.CLarXiv:2307.08303v52023
Costly Voting in the Hotelling-Downs Model
Guy Wolf, Reshef Meir
cs.GTcs.MAarXiv:2609.29869v12026
Reinforcing Agentic Creativity in Scientific Ideation with Night Science
Priyanka Kargupta, Silviu Cucerzan, Shweti Mahajan +4
cs.AIcs.CLarXiv:2609.35706v12026
GRAM: Group-wise Rank-Aware Model Merging via Subspace Alignment
Di Wu, Shuaidong Pan
cs.AIcs.CLarXiv:2610.29110v12026
f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment
Rajdeep Haldar, Lantao Mei, Guang Lin +2
cs.LGstat.MLarXiv:2602.05946v32026
Ties Matter: Meta-Evaluating Modern Metrics with Pairwise Accuracy and Tie Calibration
Daniel Deutsch, George Foster, Markus Freitag
cs.CLarXiv:2305.14324v22023
Revisiting Certified Defense with Differential Privacy on Vision Transformers
Jun Yan, Weiquan Huang, Qixian Zhang +2
cs.CRstat.AParXiv:2609.31310v12026
UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy
Yinzhen Xu, Weikang Wan, Jialiang Zhang +10
cs.ROcs.CVarXiv:2303.00938v22023
Stochastic Gradient Descent: A Nonlinear Time Series Perspective
Jiaqi Li, Zhipeng Lou, Stefan Richter +1
stat.MLcs.LGmath.STarXiv:2610.20894v12026
Non-Abelian qLDPC: TQFT Formalism, Addressable Gauging Measurement and Application to Magic State Fountain on 2D Product Codes
Guanyu Zhu, Ryohei Kobayashi, Po-Shen Hsin
quant-phcond-mat.str-elcs.ITarXiv:2601.06736v12026
Where LLM Graders Succeed and Break: Evidence from Two Computer-Science Exams
Ali Habibullah, Yazan Alshoibi, Mohammad Alshiekh +2
cs.CLcs.AIcs.CYarXiv:2609.29333v12026
An Operational Leakage Metric for Eavesdropping in Joint Sensing and Communications Systems
Nanchi Su, Xiaoye Jing, Fan Liu +3
eess.SParXiv:2609.27527v12026
An optimal control perspective on diffusion-based generative modeling
Julius Berner, Lorenz Richter, Karen Ullrich
cs.LGmath.OCstat.MLarXiv:2211.01364v32022
Disentangling Representation Evolution in Transformers through Directional Decomposition
Shwai He, Haichao Zhang, Shen Yan
cs.CLcs.LGarXiv:2609.15975v12026
On the Statistical Mechanics of Attention
Jerry Yao-Chieh Hu, Yu-An Chen, Maojiang Su +1
cs.LGcond-mat.dis-nncond-mat.stat-mecharXiv:2610.17347v12026
On the computational cost of Stochastic Gradient Langevin Dynamics
Mateusz B. Majka, Tigran Nagapetyan, Łukasz Szpruch +2
math.NAcs.NAmath.PRarXiv:2609.17750v12026
A Primal-Dual Formulation for Pricing Static Voltage Stability Services within a Unit Commitment Model
Peng Wang, Luis Badesa
eess.SYcs.SYarXiv:2609.11436v12026
The Art of Scaling Reinforcement Learning Compute for LLMs
Devvrit Khatri, Lovish Madaan, Rishabh Tiwari +6
cs.LGcs.AIarXiv:2510.13786v12025
Low-Complexity SVD-Based Precoding over Zero-Padded ISI Channels
Shuiyin Liu, Amin Sakzad
cs.ITmath.ITarXiv:2610.12784v12026
The Root Finding Problem Revisited: Beyond the Robbins-Monro procedure
Yue Yu, Moulinath Banerjee, Ya'acov Ritov
math.STstat.MEstat.THarXiv:2508.17591v12025
Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation
Yilei Tu, Zihao Li, Shaoxiong Ji +2
cs.LGcs.CLarXiv:2609.13770v12026
Analytic Gradients and Nonadiabatic Couplings for Device-Resident DMRG-QD-NEVPT2 Through Conical Intersections on a Consumer GPU
Rubén Darío Guerrero
physics.chem-phcs.ARarXiv:2609.09990v22026
Personalization Matters: Long-Horizon Conversation Agent with User-Centric Information in Online Shopping Interactions
Rena Gao, Yue Dai, Hao Guan +4
cs.MAarXiv:2610.11375v12026
Computational advantage of quantum random sampling
Dominik Hangleiter, Jens Eisert
quant-phcond-mat.quant-gascs.CCarXiv:2206.04079v42022
When Does Text Inform? Benchmarking Information-Theoretic Metrics for Multimodal Time-Series Forecasting
Emma Andrews, Gianmarco Mengaldo
cs.AIcs.ITmath.ITarXiv:2609.11282v12026
Gluon: Making Muon & Scion Great Again! (Bridging Theory and Practice of LMO-based Optimizers for LLMs)
Artem Riabinin, Egor Shulgin, Kaja Gruntkowska +1
cs.LGmath.OCstat.MLarXiv:2505.13416v12025
Distinguishing graphs with simple spectrum by homomorphism counts
Takanori Maehara
math.COcs.DMarXiv:2610.09042v12026
Tight Distributed Sketching Lower Bound for Connectivity
Huacheng Yu
cs.DScs.DCarXiv:2007.12323v12020

Every paper with a summary

When is a better LLM worth paying for? Stochastic Optimization with Switching Mixed-Fidelity Oracles

From Identification to Authentication for Micro-CSI RF Fingerprinting in OFDM Systems

PipelineRL: Faster On-policy Reinforcement Learning for Long Sequence Generation

Graph-Theoretic Bounds for Non-Linear Function Computation Broadcast

Variable-Granularity Tokenization for High-Resolution Object Detection

AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench

Compositional Information Geometry of Probabilistic Programs

Hard-Constrained Sampling on Embedded Riemannian Manifolds via Adjoint Schrödinger Bridges

Entanglement-of-formation potentials for feedback-assisted classical communication and randomness distillation

Block encoding of semiseparable matrices via their generators

Renormalization Group Flow Matching for Scalable Local Generative Modeling

Flexible-Antenna Systems: A Pinching-Antenna Perspective

Randomized Transport Maps for Model-Free Policy-Gradient Mean-Field Control

Removing spurious minima for planar features by skip connections

The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks

Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning

SAGE: Salient Factor Discovery and Generation with Visual Foundation Representations

Diffusion for World Modeling: Visual Details Matter in Atari

Beyond Sequence Order: Syntax-Informed Positional Embeddings for Transformers

What Can a Gaussian Process Design Test

Direct Preference Optimization with an Offset

The Hidden Power of Scaling Factor in LoRA Optimization

Complexity separations for optimal matchgate-Clifford synthesis

AdaMerging: Adaptive Model Merging for Multi-Task Learning

Sipser-Spielman meets Dijkgraaf-Witten: non-Abelian qLDPC codes via twisted sheaf gauge theory and almost-constant-overhead magic state fountain

Evaluation Awareness in Language Models: Representation, Verbalization, and Control

Handling plant-model mismatch in Koopman Lyapunov-based model predictive control via offset-free control framework

The Newton-Muon Optimizer

The Investment Acceleration Principle Revisited by means of a Neural Network

Generative Modeling of Stochastic Dynamics for Long-Time Evolution

On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking

3GPP-inspired HetNet Model using Poisson Cluster Process: Sum-product Functionals and Downlink Coverage

Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models

Costly Voting in the Hotelling-Downs Model

Reinforcing Agentic Creativity in Scientific Ideation with Night Science

GRAM: Group-wise Rank-Aware Model Merging via Subspace Alignment

f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment

Ties Matter: Meta-Evaluating Modern Metrics with Pairwise Accuracy and Tie Calibration

Revisiting Certified Defense with Differential Privacy on Vision Transformers

UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy

Stochastic Gradient Descent: A Nonlinear Time Series Perspective

Non-Abelian qLDPC: TQFT Formalism, Addressable Gauging Measurement and Application to Magic State Fountain on 2D Product Codes

Where LLM Graders Succeed and Break: Evidence from Two Computer-Science Exams

An Operational Leakage Metric for Eavesdropping in Joint Sensing and Communications Systems

An optimal control perspective on diffusion-based generative modeling

Disentangling Representation Evolution in Transformers through Directional Decomposition

On the Statistical Mechanics of Attention

On the computational cost of Stochastic Gradient Langevin Dynamics

A Primal-Dual Formulation for Pricing Static Voltage Stability Services within a Unit Commitment Model

The Art of Scaling Reinforcement Learning Compute for LLMs

Low-Complexity SVD-Based Precoding over Zero-Padded ISI Channels

The Root Finding Problem Revisited: Beyond the Robbins-Monro procedure

Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation

Analytic Gradients and Nonadiabatic Couplings for Device-Resident DMRG-QD-NEVPT2 Through Conical Intersections on a Consumer GPU

Personalization Matters: Long-Horizon Conversation Agent with User-Centric Information in Online Shopping Interactions

Computational advantage of quantum random sampling

When Does Text Inform? Benchmarking Information-Theoretic Metrics for Multimodal Time-Series Forecasting

Gluon: Making Muon & Scion Great Again! (Bridging Theory and Practice of LMO-based Optimizers for LLMs)

Distinguishing graphs with simple spectrum by homomorphism counts

Tight Distributed Sketching Lower Bound for Connectivity