Skip to content
Live
#Open source
Nov 4Wed
  1. Hugging Face Daily Papers65

    CrossSWE: Benchmark for testing large language models in cross-repository collaborative development

    CrossSWE benchmark tests the cross-repository consistency of large language models in cross-repository collaborative software development, including 171 instances, covering 165 repositories, 20 technical fields, and 13 programming languages. The evaluation shows that the strongest GPT-6.1 Sol only achieves 58.48% Pass@1, with cross-repository inconsistency being the main failure mode.

  5. OpenHands Blog71

    OpenHands and Snowflake introduce a workflow for training models using their own Agent harness

    OpenHands partnered with Snowflake AI Research, allowing developers to directly use the existing OpenHands Agent harness for reinforcement learning and training without rebuilding the harness in the training framework.

    Why it matters: The original text provides specific configuration methods and code locations for directly using the existing Agent harness for RL training, allowing readers to judge whether training and deployment can share a single harness.

  7. Cohere Blog

    Cohere integrates third-party open-source models into the Model Vault, providing fully controlled AI model services.

    Cohere has integrated third-party open-source models into Model Vault and Model Vault Encrypted, allowing enterprises to run Cohere models and mainstream open-source models like DeepSeek V4.1 Flash and GLM 5.3 Flash on a controlled and encrypted inference platform, with default implementation of zero-shot prompting and output data retention.

  8. Meta Engineering34

    Meta launches F3 Lightning to accelerate the large-scale production of advertising ML features

    Meta launches F3 Lightning to address bottlenecks in F3 graph publishing by decoupling feature publishing from execution, enabling independent validation deployment. It adopts optimizations such as stable compute identifiers, a single execution plan, shared memory buffers, and dense index mapping, making the production speed of extraction features approximately 3.6 times faster than F3 without increasing infrastructure compute costs.

  9. OpenAI Agents SDK releases40

    OpenAI Agents SDK v0.24.0-alpha.6 released

    OpenAI Agents SDK v0.24.0-alpha.6 released, supporting submission of work through captured Turn control, passive event handling, manual request handling, redirection and cancellation, and extending local storage session state recovery and tool policy features. New features include local storage, native output, experimental external job recovery, and tool selection, while updating the API, such as using Agent.run() instead of Runner, and unified FunctionTool callback and manual tool.

  12. Hugging Face Blog60

    IBM trains 20B small model Palette to generate slides according to its own design language

    IBM's research team fine-tunes a 20B open-source weight model, Palette, using a two-role LoRA scheme where designers write JSON briefs and encoders generate pptxgenjs code page by page to create presentations according to IBM Design Language.

    Why it matters: IBM uses synthetic data and checks to repair closed-loop training for a 20B small model to create presentations, providing a method that can be transferred to other structured outputs.

  13. Hugging Face Blog50

    StateBench: Testing how language models track state changes in long documents

    StateBench is a long-context state tracking benchmark that tests how language models maintain tracking changes in entity information within long documents. The benchmark includes four difficulty levels, ranging from simple immutable assignments to complex dependency assignments. It found that cyclic and hybrid models generalize better than Transformers on direct training tasks, but cutting-edge models like Gemini 3.8 Flash, Claude Opus 5.5, and GPT-6 Sol still fail in complex state tracking with long inputs.

  14. AWS Machine Learning Blog38

    How does Cartesia build ultra-low latency speech AI applications on AWS?

    Cartesia uses state space models (SSM) designed for real-time speech AI and AWS infrastructure to achieve sub-100ms text-to-speech and speech-to-text, supporting voice cloning for 44 languages, suitable for scenarios such as virtual assistants and customer service centers. The Sonic model generates the first audio byte in about 90ms, and the Ink model has native turn detection and noise robustness. The API interface supports real-time streaming output.

  17. NVIDIA Newsroom38

    How AI is reshaping the work of semiconductor wafer factories - engineers accelerating decision-making due to it

    AI is changing the way semiconductor wafer factories work, accelerating decision-making for engineers. NVIDIA's cuDSS library accelerates COMSOL's multiphysics simulation 10 times, Applied Materials' Ginestra platform simulation 10 times, ACE+ platform 35 times, and Siemens' Calibre lithography software simulation 17 times. NVIDIA's PhysicsNeMo framework enables Lam Research to predict plasma behavior at the millisecond level, replacing full simulations that took days.

  18. Hugging Face Blog62

    The same model with a different harness: Comparing CUGA, Hermes, and Deep Agents on AppWorld.

    The IBM team compared CUGA, Hermes, and Deep Agents using the same open-source weight model GLM-5.3-flash on 90 tasks in AppWorld, with pass rates of 81.1%, 46.7%, and 30.0%, respectively, and 20, 8, and 2 scenarios where all three variants passed.

    Why it matters: With the same model but a different harness, the task completion rate increased from 30% to 81%, and reproducible configurations and evaluation links were provided in the text.

Nov 3Tue
  1. Hugging Face Daily Papers65

    SWE-Trail: A Historical Guidance Trajectory Collection Method for Coding Agent Training

    SWE-Trail leverages past execution trajectories to guide subsequent exploration without exposing historical information to coding agents, thereby enhancing the trajectory collection effectiveness for coding agent training. This method improves the average problem-solving rate by 2.33 and 1.60 percentage points on SWE-bench Multilingual and SWE-bench Pro, respectively, using a student model with 124B parameters.

  3. Hugging Face Daily Papers65

    Hugging Face Daily Papers: Advances in Proxy Computer Graphics

    Hugging Face Daily Papers has released a report on proxy computer graphics driven by large language models, proposing a unified classification method and literature system, analyzing trends and challenges in human-machine collaboration and long-term planning. The report introduces a unified classification method for representing agent systems in different computer graphics tasks and develops an agent literature system to assist researchers in large-scale analysis of existing and new published papers.

  5. ITHome · AI

    Lenovo Kaitian has launched its first domestic AI mainframe: Zhixing KX-7000 processor + HIMO Zhi NPU LQ50.

    Lenovo Kaitea introduces its first domestic-innovation AI mainframe, equipped with Zhixin KX-7000 processor and HIMO Zhi Neng Qiang LQ50 NPU, providing 160TOPS local AI computing power, with a maximum support of 320 TOPS, capable of running 35B parameter large models. The machine is pre-installed with Tianxi AI Pro intelligent agent, supporting 7×24 digital employee services.

  7. Hugging Face Daily Papers

    ReTrace framework: Revealing the recovery behavior of computer agents through goal-directed action replay

    The ReTrace framework restores standard formal transition consistency through goal-directed action replay and controlled error injection, systematically studying the recovery behavior of autonomous models of computer agents, discovering that ideal recovery unlocks the model's potential task-completion capabilities, finding that current agents do not fully utilize their potential recovery capabilities, and that accurate model recovery can bring measurable end-to-end gains, proving that recovery is a fundamental capability for building reliable computer agents.

  9. Hugging Face Daily Papers

    Reviso: Not All Visual Evidence Should Be Given Equal Attention in Video Caption Generation

    Reviso is an intelligent video subtitle framework that prioritizes key visual evidence through hierarchical planning and active perception learning, enhancing subtitle quality and downstream video understanding capabilities. Multimodal large language models (MLLMs) generated video subtitles may overemphasize minor details while ignoring important context and key events.

  10. Hugging Face Daily Papers58

    CoworkOS: An Intelligent Agent Collaboration Framework for Real-world Automation

    CoworkOS enables human-machine collaboration and continuously improves model performance by separating strategies from execution, driving human-machine collaboration towards real-world automation. The framework performs excellently in 12 benchmarks and 6 categories of real-world applications, using GLM-5.3 as the core, and performs RSI-driven automatic post-training on Qwen3.6-35B-A3B, increasing the average score on 8 benchmarks from 33.19 to 42.95.

  11. Ai2 Blog

    StateBench: Benchmark for testing large language models to track changes in long document states

    StateBench is a benchmark for testing large language models' ability to track entity state changes in long documents, including four difficulty levels: R-trivial, non-periodic, solvable, and general finite. Research finds that recurrent and hybrid models generalize far better than Transformers when directly trained on these tasks, while cutting-edge models like Gemini 3.8 Flash, Claude Opus 5.5, and GPT-6 Sol still struggle with more complex state tracking issues when input lengths vary.

  13. QbitAI65

    China Telecom TeleAI releases a privacy camera to ensure the safety and privacy of public restrooms

    China Telecom AI Research Institute (TeleAI) has launched the 'TeleAI Privacy Camera' for the public safety field. It achieves security alerts by pushing text descriptions through AI analysis of the environment, while protecting user privacy. This product does not store or transmit original video footage and can identify violations such as fighting, smoking, and falling. Developed by Professor Li Xuelong's team, it is based on AI Flow technology, using a edge-cloud collaborative reasoning architecture and a homologous model to complete privacy information de-sensitization processing at the moment of collection.

  14. ITHome · AI

    Xiaomi-Robotics-1 Embodied Base Model Starts 'Trial Operation' at Xiaomi Youth Apartments

    The Xiaomi-Robotics-1 Embodied Base Model has started 'trial operation' at Xiaomi Youth Apartments, capable of autonomously planning tasks such as desk organization and trash cleaning. The model is pre-trained on 100,000 hours of UMI data and post-trained on 10,000 hours of cross-ontology data, supporting mobile operation and dual-arm robots, adapted for complex tasks. The Agent closed-loop system built by Xiaomi Technology achieves long-term validation with coverage of 3 rooms and over 50 tasks within 30 minutes.

  16. MarkTechPost62

    OpenAI launches Pando: a Git backend that reduces median push latency by about 80%

    OpenAI has launched Pando, a Git backend that reduces median push latency by about 80% and processes nearly 1 PB of Git data daily. Pando uses branch-level causal consistency, stores reusable data packages, and achieves high concurrency processing using only a few CPU cores, but it has not yet been open-sourced.

    Same story · 2 outlets

    How the accounts differ:OpenAI News states Pando is designed for Codex scale development; MarkTechPost mentions it reduces median push latency by about 80% and handles nearly 1PB of Git data daily.

  17. Hugging Face Blog

    Transformers Model Integration Contracts Released: Hugging Face Launches Model Integration Contracts Standard

    Transformers supports over 750 model types, its test suite includes 88,000+ CPU tests and 200,000+ GPU tests. Hugging Face releases Model Integration Contracts (MIC) standard, including compressed models (such as a 66 MB weight UMT5 fix), runnable examples (such as SmolLM text generation), and human review baselines.

  18. Anthropic Research62

    Anthropic has released the verifiable reasoning system FlashProve, generating proofs at approximately 110 tokens/second on a single H100.

    Anthropic announced the verifiable reasoning prototype FlashProve, using zkSNARK to prove that the response indeed comes from the committed model weights. For the 400B parameter Llama 4 Maverick (4-bit quantization), a single H100 generates proofs at approximately 110 tokens/second, with proofs for each 1,024 token request being about 19 MB, and verification on a 24-core CPU taking about 17 seconds.

    Same story · 4 outlets

    How the accounts differ:MarkTechPost states the proof volume is 18.78 MB; The Decoder states it is about 19 MB.

    Why it matters: Anthropic has released the measured data and Lean formal proof of the verifiable reasoning prototype FlashProve, allowing for a cross-comparison with existing zkML solutions.

  19. QbitAI

    Xiaomi's Embodied Base Model Wins Leading Technology Award at Wuzhen Summit

    Xiaomi Group Wins 'Outstanding Contribution Award' at the 2026 World Internet Conference, and Xiaomi's Embodied Base Model Wins 'Leading Technology Award'. The model is based on Xiaomi-Robotics-1 pre-training and ranked first globally in RoboCasa365 and RoboDojo evaluations. It has completed long-range validation in Xiaomi Youth Apartments, covering over 30 minutes, 3 rooms, and more than 50 tasks.