AI Research Papers
New papers daily from arXiv and Hugging Face Daily Papers, plus posts from top AI lab research blogs.
New AI research papers from arXiv and Hugging Face Daily Papers, updated every two hours.
- arXiv · 26 Oct 2026Information-Theoretic Secure Aggregation With Heterogeneous Client Quantization
Shreya Meel, Sennur Ulukus, Itzhak Tamo
- arXiv · 26 Oct 2026Learning When to Commit: Schedule Distillation for Fast Diffusion Language Models
Aidar Myrzakhan, Zhiqiang Shen
- arXiv · 26 Oct 2026SEMA-Auto: Sighted and Efficient Multi-Turn Attack with Autonomy
Mingqian Feng, Xiaodong Liu, Weiwei Yang, Chenliang Xu, Jialin Song, Qiyao Ma, Chengquan Guo, Carolyn Buractaon
- arXiv · 26 Oct 2026Multi-Objective Reinforcement Learning Using Routed Ensembles and Trajectory Attribution
Zhenshuo Zhang, Ruoxuan Xiong, Hongyang R. Zhang
- arXiv · 26 Oct 2026TRACE: Memory-Efficient Time Series Class-Incremental Learning via Temporal-Spectral Reconstruction
Junhui Mao, Junru Zhang, Liming Ye, Cheng Peng, Haoran Shi, Xiaoli Tang, Baokun Wang, Bin Dou
- arXiv · 26 Oct 2026EvoRouter: Cost-Efficient Multi-Agent Routing via Insight-Guided On-Policy Distillation
Yitao Xiao, Xu Zhang, Ye Cheng, Shaoyong Guo, Yan Sun, Ziyue Zhu, Sitao Xie, Guo Tong
- arXiv · 26 Oct 2026CANS: Capability-Preserving Neuron Steering for Large Language Models
Yucheng Wu, Chengyi Xie, Chenpeng Wang, Liangming Pan
- HF Daily Papers · 24 Oct 2026Trust Mechanisms for Offline Generative AI at the Edge: A Connectivity-Regime Framework and an Empirical Study on a Raspberry Pi 5
Georgios Feretzakis, Alexandros Papaspyridis
- HF Daily Papers · 23 Oct 2026 · ▲ 14On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models
Leon Sick, Lukas Hoyer, Yannick Strümpler, Christian Reisswig, Timo Ropinski, Federico Tombari
- HF Daily Papers · 23 Oct 2026 · ▲ 19DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning
Minho Park, Kinam Kim, Donghu Kim, Byungkun Lee, Dongyoon Hwang, Yongjae Shin, Junha Hyung, Hojoon Lee
- HF Daily Papers · 20 Oct 2026 · ▲ 6DuoLM: Fast and Effective Personalized Recommendation with Language Models
Jiang Wu, Yutong Song, Hongbo Wang, Guanghe Cao, Jeff Lei Liang
- HF Daily Papers · 18 Oct 2026 · ▲ 2How Much Feedback Is Needed to Break Template Protection? The Geometric Vulnerability of Biometric Authentication
Eliron Rahimi, Margarita Osadchy, Orr Dunkelman
- arXiv · 13 Oct 2026Rubrics from the Task, Verdicts from Evidence: Pointwise Rubric Rewards with Tool-Augmented Judges
Tianci Liu, Haoyu Wang
- arXiv · 13 Oct 2026RadarGSOcc: Doppler-Aware 3D Semantic Occupancy Prediction Using 4D Radar Tensor with Geometric-Semantic Feature Extraction
Christofel Rio Goenawan, Dong-Hee Paek, Seung-Hyun Kong
- HF Daily Papers · 13 Oct 2026 · ▲ 9ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning
Bowen Ding, Mingda Wan, Yuhan Chen, Jiyao Yuan, Qi Zhu, Futing Wang, Heyuan Deng, Fei Mi
- arXiv · 13 Oct 2026Model-Based Online Decision Making via Generative Trajectory Planning
Haldun Balim, Yilun Du, Na Li
- arXiv · 13 Oct 2026MultiAlloc: Budget-Aware Precision Allocation for KV Cache Quantization
Yangchengyu Zhou, Zhiping Wu, Runchang Jiang, Dongdong Ren, Youfang Han, Wei Zhao, Dongqi Cai, Wenbin Li
- arXiv · 13 Oct 2026Two Routes to Interoceptive Prioritisation: Dissociating Likelihood Precision and Preference Reweighting in Active Inference
St John Grimbly, Nicolas Kuske, Evert A. Boonstra, Charel van Hoof, Rowan Hodson, Benjamin Rosman, Ryan Smith, Mark Solms
- arXiv · 13 Oct 2026Does self-distillation improve reasoning?
Jason Ken Adhinarta, Raina Wu, Ashutosh Sharma, Avinash Balakrishnan, Rameswar Panda, Polina Golland, Yoon Kim, Zhang-Wei Hong
- HF Daily Papers · 13 Oct 2026 · ▲ 7ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models
Changyeon Kim, Kimin Lee, Yashraj Narang, Yijie Guo
- HF Daily Papers · 13 Oct 2026 · ▲ 110Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes
Yu Wang, Rui Dai, Wei Chen, Yi Wang, Bo Dang, Kaikui Liu, Xiangxiang Chu, Yansheng Li
- HF Daily Papers · 13 Oct 2026 · ▲ 193Agent-Reflex: Teaching Language Agents to Act Reflectively
Guanting Dong, Xinyu Yang, Jiajie Jin, Yuyang Hu, Xiaoshuai Song, Yifei Chen, Xiaoxi Li, Jiejun Tan
- HF Daily Papers · 13 Oct 2026 · ▲ 34FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching
Ruchang Yao, Shi Guo, Junhao Zhuang, Mingde Yao, Xin Cai, Jiahao Zhan, Bin Fu, Xinyuan Chen
- HF Daily Papers · 12 Oct 2026 · ▲ 29Self-Distillation with Verbal Regularization
Jiazheng Li, Yawei Li, Junru Lu, Zhenyi Shen, Di Yin, Lin Gui, Xing Sun, David Rügamer
- HF Daily Papers · 12 Oct 2026 · ▲ 10AUGUstus: Autonomous Driving VLA Model with Unified Generation and Understanding
Yuqi Ye, Caigao Jiang, Zhuonan Wang, Congyuan Pei, Chao Qu, Changhao Peng, Junhong Lin, Qize Yu
- HF Daily Papers · 10 Oct 2026 · ▲ 16LightVAE: Towards Compact and Efficient Video Autoencoders
Shiqiao Gu, Yang Yong, Fengjun Zhong, Ruihao Gong, Chengtao Lv, Xiangyu Fan, Lei Yang, Xianglong Liu
- OpenAlex · Artificial intelligence · 15 Sept 2026Beyond Efficiency: A Systematic Survey of Resource-Efficient Large Language Models
["Guangji Bai","Zheng Chai","Ling Chen","Shiyu Wang","Jiaying Lu","Nan Zhang","Tingwei Shi","Ziyang Yu","Mengdan Zhu","Yifei Zhang","Xinyuan Song","Carl Yang"]
- OpenAlex · Artificial intelligence · 1 Sept 2026AlphaBridge: Tools for the analysis of predicted biomolecular complexes
["Daniel Álvarez Salmoral","Razvan Borza","Carmen Maiella","Bjørn P. Y. Kwee","Ren Xie","Robbie P. Joosten","Maarten L. Hekkelman","Anastassis Perrakis A"]
- OpenAlex · Artificial intelligence · 24 Jul 2026Readout Genesis Standalone Synthesis: Information Epistemic Foundation, Conditioned Agency, and Meta-Readout Governance
["Yaoharee Lahtee"]
- OpenAlex · Machine learning · 21 Jun 2026Class-Discriminant Codebook Construction for Single-Token Signal Compression: A Pre-Registered Campaign Establishing a Statistically-Significant, Tax-Dependent Accuracy Lever, Its Rate-Relevance Frontier and Interior Optimum, and Its Threat- Model-Dependent Privacy Posture
["Randolph James Ferlic","Kimberly Kate Ferlic"]
From AI lab blogs
- OpenAI News · 27 Oct 2026 · labGreptile takes bug detection beyond code review with GPT-6 Astra
How Greptile uses GPT-6 Astra to test user workflows, Daybreak to strengthen security, and Codex to reduce rework.
- Meta Engineering (AI) · 26 Oct 2026 · labMeta Networking at the 2026 OCP Global Summit: Open Innovation for Scale-Up, Scale-Out, and Scale-Across AI Networks
At the 2026 Open Compute Project (OCP) Global Summit, Meta shared the networking innovations that are directly supporting our latest AI models, including Muse Wonder and Muse Spark, and our gigawatt-scale Prometheus cluster. Highlights IcePack IceCube: Meta s first liquid-cooled
- Google AI Blog · 26 Oct 2026 · labOur newest AI Quest: Mapping the human brain
Learn AI literacy via Google’s latest AI Quests lesson on neuroscience, “Polar Peaks.”
- OpenAI News · 26 Oct 2026 · labWorking with academic communities to build scientific understanding
OpenAI shares model results on the Kakeya conjecture, Exponential Time Hypothesis, and quantum chromodynamics—and how researchers can verify and build on them.
- OpenAI News · 26 Oct 2026 · labGPT-6.1 Sol helps CodeRabbit strengthen security across complex codebases
CodeRabbit uses GPT-6.1 Sol to investigate security risks across complex codebases. Its security agent helps developers review findings and proposed fixes.
- Anthropic · 26 Oct 2026 · labAnthropic files S-1 with the SEC for proposed initial public offering
Top AI blogs
Latest posts from OpenAI, Google, DeepMind, Hugging Face, BAIR, Lil'Log, Simon Willison, Import AI, Latent Space and more, via RSS.
- Latent Space · 27 Oct 2026 · blog[AINews] Anthropic files for $2T IPO in 2 weeks: 1400% growth rate, 48% of revenue through cloud partners, 85% margin, $1B op profit in Q2, $134B cash in bank and $10B lifetime burn
The S-1, the numbers, and the reactions.
- Simon Willison · 27 Oct 2026 · blogGPT-6.1 Terra
GPT-6.1 Terra It's always interesting to note which aspects of a new model are emphasized in the release announcement. In the case of GPT-6.1 Terra, OpenAI went with visual reasoning and computer use: We’re introducing GPT-6.1 Terra , a fast, efficient model that combines detaile
- Simon Willison · 27 Oct 2026 · blogQuoting Jason Koebler
Because big tech platforms essentially do not have customer support and make it impossible for their users to contact a human, many people experiencing run-of-the-mill tech problems have turned to ChatGPT. And, increasingly, ChatGPT is telling people that have normal tech support
- AWS Machine Learning Blog · 26 Oct 2026 · blogFleet-wide computer vision lifecycle at the edge with SageMaker SDK v3
Fleet-wide computer vision needs a model per camera, not one model for the whole fleet. This post presents a working Amazon SageMaker SDK v3 reference architecture that trains, quality-gates, compiles per-camera models with SageMaker Neo, and versions thousands of them, with an A
- AWS Machine Learning Blog · 26 Oct 2026 · blogGroundhog Day for AI agents: Prompt caching patterns for using OpenAI models on Amazon Bedrock
Every time an agent takes a step, it re-reads its entire context before acting. Here is how prompt caching for OpenAI models on Amazon Bedrock lets your agent remember, cutting input cost and latency without resending the same tools, instructions, and history every turn.
- AWS Machine Learning Blog · 26 Oct 2026 · blogBuild agentic retrieval on a Managed Amazon Bedrock Knowledge Base with CDK
Build enterprise agentic retrieval on a Managed Amazon Bedrock Knowledge Base with the AWS CDK: an agent that routes across two knowledge bases, retrieves through the AgentCore Gateway, and returns grounded, cited answers, with seven layers of observability and both on-demand and
- Simon Willison · 26 Oct 2026 · blogwebframe: evaluated as a scraper and a sandbox
Research: webframe: evaluated as a scraper and a sandbox webframe is a neat little project from Jeff Lindsay which lets you "run a web page like a program" - you point it at a URL or file and it executes it in a hidden headless web view and outputs console.log() to standard outpu
- NVIDIA Technical Blog · 26 Oct 2026 · blogHow NVIDIA Minerva Turns Telemetry Chaos Into Peak GPU Yield
AI Factories are some of the most technologically complex operational environments ever created. Hundreds of thousands of GPUs, NVIDIA Spectrum-X Ethernet...
- NVIDIA Technical Blog · 26 Oct 2026 · blogHow NVIDIA Mission Control 2.5 Brings Autonomous Recovery to Kubernetes
Training large-scale AI models on thousands of GPUs is a high-stakes operation where monitoring and automation must be built-in to optimize cluster resiliency...
- Import AI · 26 Oct 2026 · blogImport AI 478: Math for alignment; ProgramBench; and Mirendil shows what RSI means
What is night to a machine?
- Simon Willison · 25 Oct 2026 · blogSeam Cutter
Tool: Seam Cutter I built this weird and very specific cropping tool - it lets you create a horizontal or vertical cut across an image, then slide the two sides relative to each other. Effectively it lets you crop out a section in the middle of an image. I wanted this because I o
- Interconnects · 25 Oct 2026 · blogPodcast: Kimi K3.1 Pro, the new cyber reality, and Muse musings
#20
Frequently asked questions
Which arXiv categories are covered?
cs.AI, cs.CL and cs.LG, plus Hugging Face Daily Papers.