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)

54,901 to 54,960 of 61,280

MERRIN: A Benchmark for Multimodal Evidence Retrieval and Reasoning in Noisy Web Environments
Han Wang, David Wan, Hyunji Lee +6
cs.CLcs.AIcs.CVarXiv:2604.13418v12026
Cross-Tokenizer LLM Distillation through a Byte-Level Interface
Avyav Kumar Singh, Yen-Chen Wu, Alexandru Cioba +2
cs.CLarXiv:2604.07466v22026
Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction
Efstathios Karypidis, Spyros Gidaris, Nikos Komodakis
cs.CVarXiv:2604.11707v12026
Self-Evolving LLM Memory Extraction Across Heterogeneous Tasks
Yuqing Yang, Tengxiao Liu, Wang Bill Zhu +3
cs.CLarXiv:2604.11610v12026
Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision
Yinghui He, Simran Kaur, Adithya Bhaskar +7
cs.CLarXiv:2604.12002v22026
Domain-Specific Latent Representations Improve the Fidelity of Diffusion-Based Medical Image Super-Resolution
Sebastian Cajas, Ashaba Judith, Rahul Gorijavolu +8
cs.CVcs.AIarXiv:2604.12152v12026
Learning Versatile Humanoid Manipulation with Touch Dreaming
Yaru Niu, Zhenlong Fang, Binghong Chen +8
cs.ROarXiv:2604.13015v32026
VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization
Andrei Atanov, Jesse Allardice, Roman Bachmann +6
cs.CVcs.LGarXiv:2604.12887v12026
Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness
Tomer Ashuach, Shai Gretz, Yoav Katz +2
cs.CLarXiv:2604.12373v52026
Towards Long-horizon Agentic Multimodal Search
Yifan Du, Zikang Liu, Jinbiao Peng +5
cs.CVcs.AIarXiv:2604.12890v22026
Toward Autonomous Long-Horizon Engineering for ML Research
Guoxin Chen, Jie Chen, Lei Chen +7
cs.CLarXiv:2604.13018v22026
Exploration and Exploitation Errors Are Measurable for Language Model Agents
Jaden Park, Jungtaek Kim, Jongwon Jeong +3
cs.AIarXiv:2604.13151v12026
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
Jiacheng Liu, Xiaohan Zhao, Xinyi Shang +1
cs.SEcs.AIcs.CLarXiv:2604.14228v22026
InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis
Oliver Bentham, Vivek Srikumar
cs.CLcs.AIarXiv:2604.13201v22026
Boosting Visual Instruction Tuning with Self-Supervised Guidance
Sophia Sirko-Galouchenko, Monika Wysoczanska, Andrei Bursuc +2
cs.CVarXiv:2604.12966v12026
Forge-UGC: FX optimization and register-graph engine for universal graph compiler
Satyam Kumar, Saurabh Jha
cs.ARcs.AIcs.DCarXiv:2604.16498v12026
Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding
Eun Woo Im, Dhruv Madhwal, Vivek Gupta
cs.LGarXiv:2604.13313v12026
UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding
Fei Tang, Bofan Chen, Zhengxi Lu +8
cs.CVcs.AIcs.CLarXiv:2604.14113v12026
Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents
Kangsan Kim, Minki Kang, Taeil Kim +3
cs.AIcs.CLarXiv:2604.14004v12026
TIP: Token Importance in On-Policy Distillation
Yuanda Xu, Hejian Sang, Zhengze Zhou +3
cs.LGcs.AIarXiv:2604.14084v42026
From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space
Yuqiao Tan, Minzheng Wang, Bo Liu +5
cs.LGcs.AIcs.CLarXiv:2604.14142v12026
Geometric Context Transformer for Streaming 3D Reconstruction
Lin-Zhuo Chen, Jian Gao, Yihang Chen +8
cs.CVarXiv:2604.14141v22026
C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences
Akira Kawabata, Saku Sugawara
cs.CLcs.LGarXiv:2604.13618v12026
Three-Phase Transformer
Mohammad R. Abu Ayyash
cs.CLcs.AIcs.LGarXiv:2604.14430v12026
(1D) Ordered Tokens Enable Efficient Test-Time Search
Zhitong Gao, Parham Rezaei, Ali Cy +7
cs.CVcs.AIcs.LGarXiv:2604.15453v12026
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
Team HY-World, Chenjie Cao, Xuhui Zuo +42
cs.CVarXiv:2604.14268v12026
RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography
Mélanie Roschewitz, Kenneth Styppa, Yitian Tao +10
cs.AIarXiv:2604.15231v22026
Target-Oriented Pretraining Data Selection via Neuron-Activated Graph
Zijun Wang, Haoqin Tu, Weidong Zhou +7
cs.CLarXiv:2604.15706v12026
HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System
Tianshuo Yang, Guanyu Chen, Yutian Chen +8
cs.CVcs.AIcs.ROarXiv:2604.14125v22026
AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization
Genghan Zhang, Shaowei Zhu, Anjiang Wei +6
cs.LGcs.CLarXiv:2511.15915v22025
Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges
Xiaohua Wang, Muzhao Tian, Yuqi Zeng +20
cs.LGarXiv:2604.13602v12026
WavAlign: Enhancing Intelligence and Expressiveness in Spoken Dialogue Models via Adaptive Hybrid Post-Training
Yifu Chen, Shengpeng Ji, Qian Chen +9
cs.AIarXiv:2604.14932v12026
OneHOI: Unifying Human-Object Interaction Generation and Editing
Jiun Tian Hoe, Weipeng Hu, Xudong Jiang +2
cs.CVcs.MMarXiv:2604.14062v12026
MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation
Yan Li, Zezi Zeng, Yifan Yang +12
cs.CVcs.AIcs.CLarXiv:2604.15309v12026
GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens
Roni Itkin, Noam Issachar, Yehonatan Keypur +3
cs.CVarXiv:2604.15284v22026
TRACER: Trace-Based Adaptive Cost-Efficient Routing for LLM Classification
Adam Rida
cs.AIarXiv:2604.14531v12026
OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis
Kanzhi Cheng, Zehao Li, Zheng Ma +11
cs.AIcs.CLcs.CVarXiv:2604.15093v12026
Where does output diversity collapse in post-training?
Constantinos Karouzos, Xingwei Tan, Nikolaos Aletras
cs.CLcs.AIcs.LGarXiv:2604.16027v12026
Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents
Yining Hong, Yining She, Eunsuk Kang +2
cs.SEcs.AIcs.CRarXiv:2604.15579v22026
Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs
Sai Srinivas Kancheti, Aditya Sanjiv Kanade, Vineeth N. Balasubramanian +1
cs.CVcs.AIarXiv:2604.16060v12026
Qwen3.5-Omni Technical Report
Qwen Team
cs.CLeess.ASarXiv:2604.15804v22026
GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification
Wangjie Gan, Miao Pan, Linbo Xi +4
cs.AIcs.LGarXiv:2604.14258v32026
Beyond Prompts: Unconditional 3D Inversion for Out-of-Distribution Shapes
Victoria Yue Chen, Emery Pierson, Léopold Maillard +1
cs.CVarXiv:2604.14914v22026
An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning
Quyen Tran, Hai Nguyen, Hoang Phan +6
cs.LGcs.CVarXiv:2211.16780v42022
LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning
Bowen Ping, Zijun Chen, Tingfeng Hui +4
cs.LGcs.CLarXiv:2604.14922v12026
Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG
Yiqun Sun, Pengfei Wei, Lawrence B. Hsieh
cs.IRcs.AIcs.CLarXiv:2604.14572v32026
LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories
Zhanhao Liang, Tao Yang, Jie Wu +2
cs.CVarXiv:2604.15311v22026
Switch-KD: Visual-Switch Knowledge Distillation for Vision-Language Models
Haoyi Sun, Xiaoxiao Wang, Ning Mao +5
cs.CVarXiv:2604.14629v12026
DR$^{3}$-Eval: Towards Realistic and Reproducible Deep Research Evaluation
Qianqian Xie, Qingheng Xiong, He Zhu +16
cs.AIarXiv:2604.14683v12026
EdgeDetect: Importance-Aware Gradient Compression with Homomorphic Aggregation for Federated Intrusion Detection
Noor Islam S. Mohammad
cs.CRarXiv:2604.14663v12026
PRL-Bench: A Comprehensive Benchmark Evaluating LLMs' Capabilities in Frontier Physics Research
Tingjia Miao, Wenkai Jin, Muhua Zhang +19
cs.LGcs.AIphysics.data-anarXiv:2604.15411v12026
Learning Adaptive Reasoning Paths for Efficient Visual Reasoning
Yixu Huang, Tinghui Zhu, Muhao Chen
cs.CVcs.CLarXiv:2604.14568v12026
QuantCode-Bench: A Benchmark for Evaluating the Ability of Large Language Models to Generate Executable Algorithmic Trading Strategies
Alexey Khoroshilov, Alexey Chernysh, Orkhan Ekhtibarov +2
cs.CLarXiv:2604.15151v12026
Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips
Ido Galil, Moshe Kimhi, Ran El-Yaniv
cs.LGcs.AIcs.CVarXiv:2502.07408v22025
PerturbRx: Learning Treatment-Conditioned Latent Transitions for Patient Drug Response Prediction
Yoshitaka Inoue, Minoh Jeong, Alfred Hero +2
q-bio.QMcs.LGarXiv:2608.21349v12026
Hierarchical Codec Diffusion for Video-to-Speech Generation
Jiaxin Ye, Gaoxiang Cong, Chenhui Wang +4
cs.SDcs.CVarXiv:2604.15923v12026
TwinTrack: Post-hoc Multi-Rater Calibration for Medical Image Segmentation
Tristan Kirscher, Alexandra Ertl, Klaus Maier-Hein +3
cs.LGarXiv:2604.15950v22026
VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects
Xiangbo Gao, Sicong Jiang, Bangya Liu +12
cs.CVcs.AIcs.CLarXiv:2604.16272v22026
ArtifactNet: Detecting AI-Generated Music via Forensic Residual Physics
Heewon Oh
cs.SDeess.ASarXiv:2604.16254v22026
GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows
Jize Wang, Xuanxuan Liu, Yining Li +7
cs.CLcs.AIarXiv:2604.15715v12026

Every paper with a summary

MERRIN: A Benchmark for Multimodal Evidence Retrieval and Reasoning in Noisy Web Environments

Cross-Tokenizer LLM Distillation through a Byte-Level Interface

Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction

Self-Evolving LLM Memory Extraction Across Heterogeneous Tasks

Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision

Domain-Specific Latent Representations Improve the Fidelity of Diffusion-Based Medical Image Super-Resolution

Learning Versatile Humanoid Manipulation with Touch Dreaming

VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization

Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness

Towards Long-horizon Agentic Multimodal Search

Toward Autonomous Long-Horizon Engineering for ML Research

Exploration and Exploitation Errors Are Measurable for Language Model Agents

Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems

InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis

Boosting Visual Instruction Tuning with Self-Supervised Guidance

Forge-UGC: FX optimization and register-graph engine for universal graph compiler

Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding

UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding

Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents

TIP: Token Importance in On-Policy Distillation

From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space

Geometric Context Transformer for Streaming 3D Reconstruction

C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences

Three-Phase Transformer

(1D) Ordered Tokens Enable Efficient Test-Time Search

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography

Target-Oriented Pretraining Data Selection via Neuron-Activated Graph

HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System

AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization

Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges

WavAlign: Enhancing Intelligence and Expressiveness in Spoken Dialogue Models via Adaptive Hybrid Post-Training

OneHOI: Unifying Human-Object Interaction Generation and Editing

MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation

GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens

TRACER: Trace-Based Adaptive Cost-Efficient Routing for LLM Classification

OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis

Where does output diversity collapse in post-training?

Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents

Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs

Qwen3.5-Omni Technical Report

GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification

Beyond Prompts: Unconditional 3D Inversion for Out-of-Distribution Shapes

An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning

Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG

LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories

Switch-KD: Visual-Switch Knowledge Distillation for Vision-Language Models

DR$^{3}$-Eval: Towards Realistic and Reproducible Deep Research Evaluation

EdgeDetect: Importance-Aware Gradient Compression with Homomorphic Aggregation for Federated Intrusion Detection

PRL-Bench: A Comprehensive Benchmark Evaluating LLMs' Capabilities in Frontier Physics Research

Learning Adaptive Reasoning Paths for Efficient Visual Reasoning

QuantCode-Bench: A Benchmark for Evaluating the Ability of Large Language Models to Generate Executable Algorithmic Trading Strategies

Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips

PerturbRx: Learning Treatment-Conditioned Latent Transitions for Patient Drug Response Prediction

Hierarchical Codec Diffusion for Video-to-Speech Generation

TwinTrack: Post-hoc Multi-Rater Calibration for Medical Image Segmentation

VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects

ArtifactNet: Detecting AI-Generated Music via Forensic Residual Physics

GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows