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)

15,061 to 15,120 of 118,318

Mind the Spike: Mechanisms and Brittleness of Visual Massive Activations in Large Vision-Language Models
Jonas Ngnawé, Yann Pequignot, Sabyasachi Sahoo +3
cs.LGcs.AIcs.CLarXiv:2609.32808v12026
The Case for TPU-Accelerated Analytical Query Processing
Yeounoh Chung, Jaehyun Ha, Helena Caminal +4
cs.DBarXiv:2610.22673v12026
First Passage Attention
Yuxuan Liu
cs.CLcs.AIcs.LGarXiv:2610.22714v12026
Finding Emotions Where They Belong: Rethinking Audio Emotion Recognition through Masked Temporal Affective Grounding
Abdelrahman Mohamed, Lars Kai Hansen, Zheng-Hua Tan
cs.SDcs.AIeess.ASarXiv:2609.32804v12026
Vega: A 10-Core SoC for IoT End-Nodes with DNN Acceleration and Cognitive Wake-Up From MRAM-Based State-Retentive Sleep Mode
Davide Rossi, Francesco Conti, Manuel Eggimann +9
cs.ARcs.AIarXiv:2110.09101v12021
Sentence-Level Topic Modeling with Lexical and Contextual Evidence
Federica Granese, Serena Villata, Charles Bouveyron
cs.CLcs.LGarXiv:2610.23388v12026
The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations
Peter Hase, Harry Xie, Mohit Bansal
cs.LGcs.AIcs.CLarXiv:2106.00786v22021
Getting Motif-ated: Controllable AI Compositions from Injected Motif Prompts
Chao Peter Yang, Cynthia Rudin, Yue Jiang +2
cs.LGcs.AIcs.MMarXiv:2609.32788v12026
REALIS: A Curated Dataset for Studying the Challenges of AI Image Detection
Aleksandr Gushchin, Khaled Abud, Georgii Bychkov +5
cs.CVcs.AIarXiv:2609.32734v12026
Truth in Contrast: Calibrated Factual Evidence from Language Model Likelihoods
Ponhvoan Srey, Jason Lucas, Pittawat Taveekitworachai +2
cs.CLcs.AIarXiv:2610.23527v12026
Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer
Zhihan Liu, Miao Lu, Shenao Zhang +5
cs.LGcs.AIstat.MLarXiv:2405.16436v32024
DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding
Tianhe Ren, Yihao Chen, Qing Jiang +17
cs.CVarXiv:2411.14347v32024
SemQBench: Benchmarking Decomposition-Aware Runtime Policies for Quantum-HPC Search
Chandrachud Pati, Yogesh Simmhan
cs.ETarXiv:2610.22886v12026
Learning to Refer: Client-Resolved Generation for Privacy-Aware Language Models
Jeongho Yoon, Chanhee Park, Yongchan Chun +5
cs.CRcs.AIarXiv:2609.32706v12026
Understanding KV Residency in Production-Scale Agentic LLM Workloads
Mayank Arya, Agrim Bari, Anjaly Parayil +4
cs.DCarXiv:2610.22863v12026
Multi-level Monte Carlo for continuous time Markov chains, with applications in biochemical kinetics
David F. Anderson, Desmond J. Higham
math.PRcs.NAmath.NAarXiv:1107.2181v32011
Gradient-Guided Decoupled Adaptation for Geospatial Vision-Language Models
Dongdong Wang, Deepak Balakrishnan, Ravi Srinivasan +1
cs.CVcs.AIcs.CLarXiv:2609.32737v12026
DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation
Chong Zeng, Yue Dong, Pieter Peers +3
cs.CVcs.GRarXiv:2402.11929v22024
How Far Do Persona Effects Generalize in Language Models?
Yufan Zhou, Yuxuan Liu, Enze Ma +6
cs.CLcs.AIarXiv:2609.32758v12026
Belief-Trajectory Energy: Measuring the Path to a Prediction
Jiahao Ying, Wei Tang, Boxian Ai +7
cs.CLarXiv:2610.05114v12026
LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations
Mohan Li, Chengyu Yu, Francesco Sovrano +2
cs.CLcs.AIarXiv:2609.32717v22026
Human-AI Collaborative Essay Scoring: A Dual-Process Framework with LLMs
Changrong Xiao, Wenxing Ma, Qingping Song +4
cs.CLcs.AIarXiv:2401.06431v22024
Jarvis: Coordination Deserves a Brain of Its Own in Agentic Interactive Models
Yuxiang Wang, Shengbo Cai, Zhixian Zhao +7
cs.SDarXiv:2610.23804v12026
MetaDB: Putting File-System Structure Back into Distributed Databases
Zebin Ren, Biao Cao, Kang Chen +10
cs.DBcs.DCarXiv:2610.32247v12026
Summaries:简体中文
FedSkillGit: Federated Skill Evolution via Version Control
Boxun Lan, Jiamei Li, Weijian Li +5
cs.AIarXiv:2610.21348v12026
Loop to Look Better: Learning Adaptive Depth for Question-Guided Perception in Vision-Language Models
Wencheng Ye, Anning Hu, Hongye Fang +2
cs.CVarXiv:2610.30824v12026
ANTE: Anticipate, Then Execute -- Learning Internal World Models for Coding Agents from Verified Beliefs
Yi Ge, Kangrui Ruan, Jifan Chen +6
cs.LGarXiv:2610.15368v12026
Mind the Tail: Data Selection Through Sparse Concepts
Ziheng Zhang, Neha Hulkund, Colin Lee +7
cs.CVarXiv:2610.21007v12026
GeoFix: Geometry Fixing for 4D Consistent Generation
Yeobin Hong, Hyojun Go, Dohun Lee +7
cs.CVcs.AIcs.LGarXiv:2610.14293v12026
Stochastic Teacher Intervention for Agentic On-Policy Distillation
Junnan Liu, Linhao Luo, Zhijun Chen +3
cs.CLcs.AIarXiv:2610.10878v12026
ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills
Hongxing Li, Dingming Li, Yixin Li +6
cs.CVcs.CLarXiv:2610.12403v12026
PyCache Trap: The Inspection-Execution Gap in Agent Skill Scanners
Jie Liao, Simeng Qin, Wenqi Ren +5
cs.CRcs.SEarXiv:2610.10612v12026
On-Policy Distillation with Negative-Policy Rollouts
Jaehui Hwang, Dongyoon Han, Sangdoo Yun +1
cs.LGarXiv:2610.07874v12026
LocAttMamba: A Low-Complexity Mamba Framework with Attention-Based Multi-AP Fusion for Indoor Localization
MohammadMahdi Ghadaksaz, Mohammad Farzanullah, Melike Erol-Kantarci
cs.NIarXiv:2610.05673v12026
ECoMEM: Explicit Concept Memory for Memory-Dependent Robot Control
Yize Liu, Ke Wang, Mac Schwager +2
cs.ROarXiv:2610.00801v12026
From Solo to Social Learning: Characterizing Recursive Social Improvement in LLMs
Kunal Jha, Max Kleiman-Weiner, Natasha Jaques
cs.MAcs.AIcs.LGarXiv:2609.38516v12026
FreSia: Frequency-Semantic Instantiation and Alignment for Multivariate Time Series Analysis
Yubo Wang, Hui He, Hezhe Qiao +2
cs.AIarXiv:2610.05726v12026
When Do Biological Reasoning Models Use Their Biological Inputs?
Ada Fang, Nikitha Thoduguli, Lukas Fesser +3
cs.LGarXiv:2610.00898v12026
ExpVoyager: Direct Experience Navigation for Dynamic Agent Skill Synthesis
Kwangwook Seo, Dongha Lee
cs.CLarXiv:2609.32630v12026
Where MLLMs Fail and Why: Causal Task Decomposition for Capability Failure Diagnosis
Xia Hu, Brian Potetz, Chun-Ta Lu +6
cs.CLcs.AIcs.CVarXiv:2609.38851v12026
Reliability-aware Cross-sample Enhancement for Robust Multimodal Sentiment Analysis
Menghua Jiang, Haokai Gao, Xiangui Kang +2
cs.LGarXiv:2609.30470v12026
Emergent Collusion in Long-Horizon LLM Agent Interaction
Xinrui Shi, Yanzhe Zhang, Diyi Yang
cs.AIcs.CLarXiv:2609.24967v12026
SkillVine: Agent Skill Evolution via Branching Exploration
Kaiwei Liu, Jiqian Dong, Liran Dong +7
cs.AIarXiv:2609.32731v12026
High-Order Sinusoidal Modeling for Precise Parameter Refinement
Shaowen Chen, Tomoki Toda
eess.SPeess.ASarXiv:2610.21643v12026
To Solve Bilevel Optimization with Nonconvex Lower Levels, We Need Second-Order Stationarity
Zhiyao Zhang, Menglu Yu, Alvaro Velasquez +2
cs.LGarXiv:2609.30501v12026
One-Step Generative CSI Prediction
Mehdi Sattari, Javad Aliakbari, Alexandre Graell i Amat +1
eess.SParXiv:2609.17033v12026
AdamX: Cosine similarity meets gradient descent
Francisco Caldas, Ruben Belo, Cláudia Soares
cs.LGmath.OCarXiv:2609.11867v12026
Giving Credit Where It's Due: Redundancy-Aware Learning for Efficient Reasoning
Yuqing Zhou, Hong Wang, Manqing Mao +8
cs.CLcs.LGarXiv:2609.27156v12026
Violet: Enabling Full Virtualization for M-mode RTOS on RISC-V
Taro Kito, Ryosuke Yamamoto, Keisuke Horii +2
cs.OSarXiv:2609.09833v12026
CLS Hardness of 2D Min-Max Optimization with Product Constraints
Alkis Kalavasis, Panagiotis Patsilinakos, Stratis Skoulakis +1
cs.GTcs.CCarXiv:2610.18678v12026
PhysiCalWorld: In-Context Physics Calibration for World Models
Yunhao Luo, Wentao He, Yinpei Dai +5
cs.ROcs.AIcs.CVarXiv:2610.30125v12026
AI-Aided ESPRIT for Joint DoA Estimation and Uncertainty Extraction
Raz Zohar, Nir Shlezinger
eess.SParXiv:2609.17059v12026
Unified Multi-Layer Subspace Modeling for Cross-Domain OOD Detection
Gerhard Krumpl, Henning Avenhaus, Horst Possegger
cs.CVarXiv:2609.06785v12026
Timestep Weighting: A Hidden Key to Effective ELBO-Based Flow-Matching RL
Qinwei Ma, Jingzhe Shi, Simin Fan +2
cs.LGcs.AIcs.CVarXiv:2609.32665v22026
CAPE - Context-Aware Prioritization Engine for Vulnerability Scoring and Management
Rakesh Podder, Viktoria Koscinski, Indrajit Ray
cs.CRcs.SEarXiv:2610.13071v12026
R2VC: Modular Fact-Checking with Retrieval, Verification, and Confidence Calibration
Dhruv Dixit, Paritosh Pandey
cs.CLcs.LGarXiv:2609.11955v12026
GreenPipe: Power Modeling for Containerized DNN Inference on Kubernetes Edge Nodes
Mengxue Wang, Peini Liu, Amir Taherkordi +1
cs.DCcs.PFarXiv:2609.04952v12026
HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization
Jianzhi Shen, Keyu Mao, Minghao Shao +7
cs.CLarXiv:2609.09835v12026
Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptation
Deepak Sridhar, Yi Li, Kartikeya Bhardwaj +7
cs.CVarXiv:2610.11067v12026
Atlas: Algorithm-Hardware Co-Design for On-Device City-Scale 3D Gaussian Splatting in VR
He Zhu, Zheng Liu, Xingyang Li +8
cs.ARarXiv:2609.02352v12026

Every paper with a summary

Mind the Spike: Mechanisms and Brittleness of Visual Massive Activations in Large Vision-Language Models

The Case for TPU-Accelerated Analytical Query Processing

First Passage Attention

Finding Emotions Where They Belong: Rethinking Audio Emotion Recognition through Masked Temporal Affective Grounding

Vega: A 10-Core SoC for IoT End-Nodes with DNN Acceleration and Cognitive Wake-Up From MRAM-Based State-Retentive Sleep Mode

Sentence-Level Topic Modeling with Lexical and Contextual Evidence

The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations

Getting Motif-ated: Controllable AI Compositions from Injected Motif Prompts

REALIS: A Curated Dataset for Studying the Challenges of AI Image Detection

Truth in Contrast: Calibrated Factual Evidence from Language Model Likelihoods

Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer

DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding

SemQBench: Benchmarking Decomposition-Aware Runtime Policies for Quantum-HPC Search

Learning to Refer: Client-Resolved Generation for Privacy-Aware Language Models

Understanding KV Residency in Production-Scale Agentic LLM Workloads

Multi-level Monte Carlo for continuous time Markov chains, with applications in biochemical kinetics

Gradient-Guided Decoupled Adaptation for Geospatial Vision-Language Models

DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation

How Far Do Persona Effects Generalize in Language Models?

Belief-Trajectory Energy: Measuring the Path to a Prediction

LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations

Human-AI Collaborative Essay Scoring: A Dual-Process Framework with LLMs

Jarvis: Coordination Deserves a Brain of Its Own in Agentic Interactive Models

MetaDB: Putting File-System Structure Back into Distributed Databases

FedSkillGit: Federated Skill Evolution via Version Control

Loop to Look Better: Learning Adaptive Depth for Question-Guided Perception in Vision-Language Models

ANTE: Anticipate, Then Execute -- Learning Internal World Models for Coding Agents from Verified Beliefs

Mind the Tail: Data Selection Through Sparse Concepts

GeoFix: Geometry Fixing for 4D Consistent Generation

Stochastic Teacher Intervention for Agentic On-Policy Distillation

ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills

PyCache Trap: The Inspection-Execution Gap in Agent Skill Scanners

On-Policy Distillation with Negative-Policy Rollouts

LocAttMamba: A Low-Complexity Mamba Framework with Attention-Based Multi-AP Fusion for Indoor Localization

ECoMEM: Explicit Concept Memory for Memory-Dependent Robot Control

From Solo to Social Learning: Characterizing Recursive Social Improvement in LLMs

FreSia: Frequency-Semantic Instantiation and Alignment for Multivariate Time Series Analysis

When Do Biological Reasoning Models Use Their Biological Inputs?

ExpVoyager: Direct Experience Navigation for Dynamic Agent Skill Synthesis

Where MLLMs Fail and Why: Causal Task Decomposition for Capability Failure Diagnosis

Reliability-aware Cross-sample Enhancement for Robust Multimodal Sentiment Analysis

Emergent Collusion in Long-Horizon LLM Agent Interaction

SkillVine: Agent Skill Evolution via Branching Exploration

High-Order Sinusoidal Modeling for Precise Parameter Refinement

To Solve Bilevel Optimization with Nonconvex Lower Levels, We Need Second-Order Stationarity

One-Step Generative CSI Prediction

AdamX: Cosine similarity meets gradient descent

Giving Credit Where It's Due: Redundancy-Aware Learning for Efficient Reasoning

Violet: Enabling Full Virtualization for M-mode RTOS on RISC-V

CLS Hardness of 2D Min-Max Optimization with Product Constraints

PhysiCalWorld: In-Context Physics Calibration for World Models

AI-Aided ESPRIT for Joint DoA Estimation and Uncertainty Extraction

Unified Multi-Layer Subspace Modeling for Cross-Domain OOD Detection

Timestep Weighting: A Hidden Key to Effective ELBO-Based Flow-Matching RL

CAPE - Context-Aware Prioritization Engine for Vulnerability Scoring and Management

R2VC: Modular Fact-Checking with Retrieval, Verification, and Confidence Calibration

GreenPipe: Power Modeling for Containerized DNN Inference on Kubernetes Edge Nodes

HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization

Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptation

Atlas: Algorithm-Hardware Co-Design for On-Device City-Scale 3D Gaussian Splatting in VR