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)

59,401 to 59,460 of 61,255

LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
Yifan Dai, Zhenhua Wu, Bohan Zeng +18
cs.CLcs.CVarXiv:2605.22012v12026
WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World Models
Bohai Gu, Taiyi Wu, Yueyang Yuan +9
cs.CVarXiv:2605.25077v12026
Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis
Yixuan Yang, Zhen Luo, Wanshui Gan +5
cs.CVcs.GRarXiv:2605.18451v12026
Interactive Evaluation Requires a Design Science
Keyang Xuan, Peiyang Song, Pan Lu +10
cs.AIarXiv:2605.17829v12026
LatentUMM: Dual Latent Alignment for Unified Multimodal Models
Yinyi Luo, Wenwen Wang, Hayes Bai +2
cs.CVarXiv:2605.17766v12026
TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization
Chonghao Zhong, Linfeng Shi, Hua Chen +4
cs.CVcs.PFarXiv:2605.20150v22026
TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload
Zhiben Chen, Youpeng Zhao, Yang Sui +2
cs.CLarXiv:2605.20179v12026
MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
Hyunji Lee, Justin Chih-Yao Chen, Joykirat Singh +3
cs.CLcs.AIarXiv:2605.18565v22026
Mem-$π$: Adaptive Memory through Learning When and What to Generate
Xiaoqiang Wang, Chao Wang, Hadi Nekoei +5
cs.CLcs.AIarXiv:2605.21463v12026
Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines
Alimurtaza Mustafa Merchant, Krish Veera, Sajal Kumar Goyla +3
cs.AIarXiv:2605.20630v12026
You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
Zhepei Wei, Xinyu Zhu, Wei-Lin Chen +3
cs.LGcs.CLarXiv:2605.21468v12026
FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching
Jangho Park, Geon Yeong Park, Gihyun Kwon +1
cs.CVarXiv:2605.20910v12026
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
Dong Chen, Fangyun Wei, Ziyu Wan +18
cs.CVarXiv:2605.21573v12026
FashionLens: Toward Versatile Fashion Image Retrieval via Task-Adaptive Learning
Haokun Wen, Xuemeng Song, Xinghao Xie +3
cs.CVcs.MMarXiv:2605.22552v12026
ACL-Verbatim: hallucination-free question answering for research
Gábor Recski, Szilveszter Tóth, Nadia Verdha +2
cs.CLcs.AIcs.SEarXiv:2605.21102v12026
SceneAligner: 3D-Grounded Floorplan Localization in the Wild
Junhyeong Cho, Ruojin Cai, Hadar Averbuch-Elor
cs.CVcs.AIcs.LGarXiv:2605.22581v12026
WorldKV: Efficient World Memory with World Retrieval and Compression
Jung Yi, Minjae Kim, Paul Hyunbin Cho +3
cs.CVarXiv:2605.22718v12026
The Expense of Seeing: Attaining Trustworthy Multimodal Reasoning Within the Monolithic Paradigm
Karan Goyal
cs.CVcs.AIarXiv:2604.20665v22026
CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models
León Begiristain, Olaf Dünkel, Adam Kortylewski
cs.CVarXiv:2605.23699v12026
ETCHR: Editing To Clarify and Harness Reasoning
Beichen Zhang, Yuhong Liu, Jinsong Li +3
cs.CVcs.AIcs.CLarXiv:2605.23897v12026
SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills
Yingtie Lei, Zhongwei Wan, Jiankun Zhang +13
cs.AIarXiv:2605.24117v12026
Breaking the Chains of Probability: Neutrosophic Logic as a New Framework for Epistemic Uncertainty in Large Language Models
Maikel Yelandi Leyva-Vázquez, Florentin Smarandache
cs.AIcs.CLcs.LGarXiv:2605.24053v12026
SPACENUM: Revisiting Spatial Numerical Understanding in VLMs
Jianshu Zhang, Yijiang Li, Huifeixin Chen +4
cs.AIarXiv:2605.23898v12026
Measuring the Depth of LLM Unlearning via Activation Patching
Jaeung Lee, Dohyun Kim, Jaemin Jo
cs.CLcs.AIcs.LGarXiv:2605.24614v12026
Pantheon360: Taming Digital Twin Generation via 3D-Aware 360° Video Diffusion
Ting-Hsuan Chen, Ying-Huan Chen, Tao Tu +10
cs.CVarXiv:2605.25449v32026
Does Seeing More Mean Knowing More? Mono-Anchored Advantage Normalization for Multi-Source Visual Reasoning
Fanhu Zeng, Zhicong Luo, Zefan Wang +3
cs.CVarXiv:2605.25437v12026
When Tool-Backed Skill Retrieval Fails: Source-Style Collapse in Executable Capability Retrieval
Yiqi Liu, Joseph James, Yang Wang +2
cs.LGcs.IRarXiv:2608.16502v12026
Echo-Forcing: A Scene Memory Framework for Interactive Long Video Generation
Mingqiang Wu, Weilun Feng, Zhefeng Zhang +8
cs.CVarXiv:2605.16003v12026
ClinSeekAgent: Automating Multimodal Evidence Seeking for Agentic Clinical Reasoning
Juncheng Wu, Letian Zhang, Yuhan Wang +5
cs.CLarXiv:2605.20176v12026
Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary Enhancement
Dingwei Chen, Zefang Zong, Zhipeng Ma +5
cs.CLarXiv:2605.26952v12026
AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling
Yiheng Li, Zhuo Li, Ruibing Hou +4
cs.CVcs.AIarXiv:2605.29488v22026
Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning
Chun-Hsiao Yeh, Shengyi Qian, Manchen Wang +3
cs.CVcs.AIarXiv:2605.30231v12026
OSP-Next: Efficient High-Quality Video Generation with Sparse Sequence Parallelism, HiF8 Quantization, and Reinforcement Learning
Yunyang Ge, Xianyi He, Zezhong Zhang +4
cs.CVarXiv:2605.28691v12026
How LoRA Remembers? A Parametric Memory Law for LLM Finetuning
Ziwen Xu, Haiwen Hong, Linsong Yu +4
cs.CLcs.AIcs.CVarXiv:2605.30260v12026
Why Far Looks Up: Probing Spatial Representation in Vision-Language Models
Cheolhong Min, Jaeyun Jung, Daeun Lee +5
cs.CVarXiv:2605.30161v12026
A Multi-AI-agent Framework Enabling End-to-end Finite Element Analysis for Solid Mechanics Problems
Titu Ranjan Sarker, Muhammed Jawaad Zulqernine, Ling Yue +3
cs.AIarXiv:2606.00138v12026
SurGe: Improved Surface Geometry in Point Maps
Karim Knaebel, Gonzalo Martin Garcia, Christian Schmidt +4
cs.CVarXiv:2605.31577v12026
PEEK: Picking Essential frames via Efficient Knowledge distillation
Killian Steunou, Anas Filali Razzouki, Khalil Guetari +2
cs.CVarXiv:2605.31029v12026
Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer
Ke Lei, Yu Zhang, Changhao Pan +4
eess.AScs.MMcs.SDarXiv:2605.30940v12026
Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?
Liyang Li, Muzhi Zhu, Zhiyue Zhao +5
cs.CVarXiv:2606.01247v12026
Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning
Jiapeng Zhu, Jianxiang Yu, Yibo Zhao +5
cs.CLarXiv:2605.28424v12026
Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling
Xinglin Wang, Hao Lin, Shaoxiong Feng +9
cs.CLarXiv:2605.27030v12026
PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft
Yuchen Guo, Junli Gong, Weicheng Wang +3
cs.AIarXiv:2605.27762v22026
Lost in Sampling: Assessing Lexical Reachability in LLMs via the Word Coverage Score (WCS)
Samer Awad, Javier Conde, Carlos Arriaga +3
cs.CLcs.AIarXiv:2605.27268v12026
Self-Improving Language Models with Bidirectional Evolutionary Search
Guowei Xu, Zhenting Qi, Huangyuan Su +4
cs.CLarXiv:2605.28814v12026
SmartDirector: Keyframe-Conditioned Cinematic Video Generation with Narrative Pacing Control
Zhida Zhang, Jie Ma, Zhan Peng +5
cs.CVcs.AIarXiv:2605.27891v12026
From Pixels to Words -- Towards Native One-Vision Models at Scale
Haiwen Diao, Jiahao Wang, Penghao Wu +18
cs.CVarXiv:2605.28820v12026
FRAPPE: Full Input, Residual Output Autoencoding with Projection Pursuit Encoder
Dan Jacobellis, Neeraja J. Yadwadkar
eess.IVarXiv:2605.28992v12026
CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists
Junlin Yang, Dylan Zhang, Xiangchen Song +7
cs.AIcs.CLarXiv:2605.26029v22026
Xetrieval: Mechanistically Explaining Dense Retrieval
Zhixin Cai, Jun Bai, Yang Liu +7
cs.AIcs.IRarXiv:2605.29507v12026
Colored Noise Diffusion Sampling
Hadar Davidson, Noam Issachar, Sagie Benaim
cs.CVarXiv:2605.30332v12026
Linearizing Vision Transformer with Test-Time Training
Yining Li, Dongchen Han, Zeyu Liu +3
cs.CVarXiv:2605.02772v22026
Exploring Autonomous Agentic Data Engineering for Model Specialization
Yujie Luo, Xiangyuan Ru, Jingsheng Zheng +10
cs.CLcs.AIcs.IRarXiv:2605.30407v22026
SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search
Yunbo Tang, Chengyi Yang, Shiyu Liu +4
cs.AIcs.CLcs.LGarXiv:2605.29796v32026
VLM3: Vision Language Models Are Native 3D Learners
Zhipeng Cai, Zhuang Liu, Yunyang Xiong +3
cs.CVcs.AIarXiv:2605.30561v12026
Adapting Multilingual Embedding Models to Turkish via Cross-Lingual Tokenizer Surgery and Offline Distillation
M. Ali Bayram, Banu Diri, Savaş Yıldırım
cs.CLarXiv:2605.29992v12026
Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents
Ziyan Liu, Zhezheng Hao, Yeqiu Chen +7
cs.AIarXiv:2605.30159v12026
Trust-Region Behavior Blending for On-Policy Distillation
Daniil Plyusov, Alexey Gorbatovski, Alexey Malakhov +4
cs.LGcs.AIarXiv:2605.31159v12026
MindZero: Learning Online Mental Reasoning With Zero Annotations
Shunchi Zhang, Jin Lu, Chuanyang Jin +3
cs.AIcs.MAarXiv:2606.00240v12026
LVSA: Training-Free Sparse Attention for Long Video Diffusion
Gael Glorian, Ioannis Lamprou, Zhen Zhang +2
cs.CVcs.LGarXiv:2605.31057v12026

Every paper with a summary

LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning

WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World Models

Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis

Interactive Evaluation Requires a Design Science

LatentUMM: Dual Latent Alignment for Unified Multimodal Models

TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization

TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload

MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems

Mem-$π$: Adaptive Memory through Learning When and What to Generate

Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines

You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories

FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching

Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models

FashionLens: Toward Versatile Fashion Image Retrieval via Task-Adaptive Learning

ACL-Verbatim: hallucination-free question answering for research

SceneAligner: 3D-Grounded Floorplan Localization in the Wild

WorldKV: Efficient World Memory with World Retrieval and Compression

The Expense of Seeing: Attaining Trustworthy Multimodal Reasoning Within the Monolithic Paradigm

CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models

ETCHR: Editing To Clarify and Harness Reasoning

SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills

Breaking the Chains of Probability: Neutrosophic Logic as a New Framework for Epistemic Uncertainty in Large Language Models

SPACENUM: Revisiting Spatial Numerical Understanding in VLMs

Measuring the Depth of LLM Unlearning via Activation Patching

Pantheon360: Taming Digital Twin Generation via 3D-Aware 360° Video Diffusion

Does Seeing More Mean Knowing More? Mono-Anchored Advantage Normalization for Multi-Source Visual Reasoning

When Tool-Backed Skill Retrieval Fails: Source-Style Collapse in Executable Capability Retrieval

Echo-Forcing: A Scene Memory Framework for Interactive Long Video Generation

ClinSeekAgent: Automating Multimodal Evidence Seeking for Agentic Clinical Reasoning

Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary Enhancement

AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling

Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning

OSP-Next: Efficient High-Quality Video Generation with Sparse Sequence Parallelism, HiF8 Quantization, and Reinforcement Learning

How LoRA Remembers? A Parametric Memory Law for LLM Finetuning

Why Far Looks Up: Probing Spatial Representation in Vision-Language Models

A Multi-AI-agent Framework Enabling End-to-end Finite Element Analysis for Solid Mechanics Problems

SurGe: Improved Surface Geometry in Point Maps

PEEK: Picking Essential frames via Efficient Knowledge distillation

Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer

Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?

Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning

Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling

PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft

Lost in Sampling: Assessing Lexical Reachability in LLMs via the Word Coverage Score (WCS)

Self-Improving Language Models with Bidirectional Evolutionary Search

SmartDirector: Keyframe-Conditioned Cinematic Video Generation with Narrative Pacing Control

From Pixels to Words -- Towards Native One-Vision Models at Scale

FRAPPE: Full Input, Residual Output Autoencoding with Projection Pursuit Encoder

CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists

Xetrieval: Mechanistically Explaining Dense Retrieval

Colored Noise Diffusion Sampling

Linearizing Vision Transformer with Test-Time Training

Exploring Autonomous Agentic Data Engineering for Model Specialization

SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search

VLM3: Vision Language Models Are Native 3D Learners

Adapting Multilingual Embedding Models to Turkish via Cross-Lingual Tokenizer Surgery and Offline Distillation

Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents

Trust-Region Behavior Blending for On-Policy Distillation

MindZero: Learning Online Mental Reasoning With Zero Annotations

LVSA: Training-Free Sparse Attention for Long Video Diffusion