Knowledge catalogue
arXiv:2609.30670v1 Announce Type: new Abstract: Streaming video understanding requires models to interpret evidence as it arrives, yet current evaluations often report task scores without specifying w
server : allow RANK pooling batch splitting for causal LLM rerankers (ie. Qwen3 and Qwen3-VL) (#28876) server : allow splitting RANK pooling for causal LLM rerankers Rerank models fall into two catego
New open source Jev like model for running on local devices from a group called Supersonic Labs. It's a 144M param local non-generative local classifier. From their site: Julia 1 opens our research in
https://huggingface.co/internlm/Intern-Decision-0.8B Intern-Decision-4B Demo | Model Weights | GitHub Intern-Decision-4B is a multimodal structured decision model fine-tuned from Qwen3.5-4B. It accept
We comprehensively evaluated 16 recent frontier VLMs - including Opus 5.5 and GPT-6 Sol/Luna - on whether higher effort led to better document parsing performance. Higher effort typically leads to imp
Yann LeCun's lab borrowed a trick from the human brain and more than doubled how often an AI found its way to a goal. The paper is called Temporal Straightening for Latent Planning, from NYU with Brow
arXiv:2609.30215v1 Announce Type: cross Abstract: We prove nearly quadratic lower bounds for randomized algorithms for linear optimization and uniform sampling over convex bodies in the membership ora
arXiv:2609.29621v1 Announce Type: new Abstract: Computer-aided design is central to industrial manufacturing, and much of a designer's daily work consists of editing existing models from multimodal re
arXiv:2609.30009v1 Announce Type: cross Abstract: Financial institutions operate under dense, frequently amended rulebooks, and answering a compliance question correctly requires not only fluency but
arXiv:2609.28908v1 Announce Type: cross Abstract: Agent behavior depends on the harness surrounding a language model, but it remains unclear whether language models can reliably improve such harnesses
Check out this week's updates and releases: — Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, two of our most expressive audio generation models yet — Gemini 3.8 Live with Live Avatar, bringing ne
arXiv:2609.29932v1 Announce Type: cross Abstract: Resting-state functional connectivity (FC) is widely used to classify brain phenotypes and disorders. Most pipelines use the full connectome and seek
arXiv:2609.29625v1 Announce Type: new Abstract: Across seven public educational prediction datasets, three passed all four pre-modeling reliability checks; the remaining four either failed group-aware
arXiv:2603.11351v2 Announce Type: replace-cross Abstract: In dynamic open-world environments, autonomous agents often encounter novelties that hinder their ability to find plans to achieve their goals
arXiv:2609.28854v1 Announce Type: cross Abstract: Language-model agents increasingly answer questions over customer-relationship management (CRM) records, such as whether to qualify a sales lead. We i
arXiv:2609.29715v1 Announce Type: cross Abstract: Surrogate models are often chosen during development and then left in place as new measurements arrive. That practice becomes risky when noise, input
arXiv:2609.28522v1 Announce Type: cross Abstract: Modern conformal forecasting systems often maintain several adaptive pipelines that differ in base forecasters, conformity scores, calibration windows
arXiv:2609.28757v1 Announce Type: cross Abstract: An estimated 1 billion people worldwide live with vision impairment, yet current vision-language models (VLMs) produce descriptions too vague for safe
arXiv:2609.29522v1 Announce Type: new Abstract: Tool-using language-model agents increasingly mutate schedulers, data pipelines, object stores, and access-control systems. Between an agent's read and
arXiv:2609.26758v2 Announce Type: replace Abstract: Typed decision models are built for settings where model outputs are consumed directly by software. Instead of generating free-form text, they retur
arXiv:2609.28335v1 Announce Type: new Abstract: Claims about AI safety reach audiences well beyond the AI community, yet many rely on opaque evidence or static assessments, when supporting evidence is
System-wide Dictation on Apple devices runs entirely on-device, and the speech it transcribes reaches the foundation model through a tokenizer: an encoder that maps short windows of waveform onto the
arXiv:2609.26926v1 Announce Type: cross Abstract: Large-scale text annotation brings expert insight to millions of documents, often through a codebook that AI annotators follow. Developing a robust co
arXiv:2609.28110v1 Announce Type: cross Abstract: Dental cone-beam computed tomography (CBCT) systems often employ detector configurations that provide a truncated field of view (FOV) that only captur
arXiv:2609.27118v1 Announce Type: new Abstract: Greenhouse climate management aims to improve crop production while limiting energy use. This requires knowing how a crop will respond before conditions
arXiv:2601.22029v2 Announce Type: replace Abstract: We introduce a new multivariate statistical problem that we refer to as the Ensemble-conditioned Inverse Problem (EIP). The aim of EIP is to invert
arXiv:2609.28049v1 Announce Type: cross Abstract: Video understanding is usually benchmarked on curated, single-actor, or professionally filmed clips, and a strong score there is routinely read as evi
arXiv:2609.27173v1 Announce Type: new Abstract: Solving complex tasks in domains such as science, medicine, law, and finance often requires assembling interdependent information scattered across vast,
arXiv:2609.27248v1 Announce Type: new Abstract: Next-token prediction has enabled highly fluent autoregressive language models, but it represents global structure only indirectly through sequential fa
arXiv:2609.27088v1 Announce Type: new Abstract: Elongate multi-legged robots use coordinated body waves and distributed legs to move through cluttered terrestrial environments. However, as housing act
arXiv:2609.26929v1 Announce Type: new Abstract: People hold diverse, sometimes conflicting values, so no single aligned model can satisfy everyone. Pluralistic alignment therefore calls for steerable
In real-time streaming, every millisecond counts. For example, at 30 frames per second (fps), developers have a strict frame budget of just 33.3 ms (and only 16.6 ms at 60 fps) to ingest camera frames
https://huggingface.co/bartowski/LensVLM-9B-GGUF LensVLM-9B LensVLM is a 9B Vision Language Model (VLM) that scans compressed images of text, then selectively expands only the relevant pages to their
arXiv:2608.28021v2 Announce Type: replace-cross Abstract: Large language models increasingly author Infrastructure-as-Code (IaC), where one insecure default is provisioned straight into production. Pr
arXiv:2609.26502v1 Announce Type: cross Abstract: Deep generative models are widely reported to enable de novo crystal structure prediction (CSP), but their capability has not been measured consistent
arXiv:2609.25010v1 Announce Type: cross Abstract: Marketers increasingly use large language models (LLMs) as 'synthetic personas' to predict how an audience will react to a piece of copy before it shi
arXiv:2609.25152v1 Announce Type: new Abstract: Deep Imbalanced Regression (DIR) addresses a common failure mode of regression models: target distributions are highly non-uniform, causing models to pe
arXiv:2609.25500v1 Announce Type: new Abstract: Training data quantity and quality greatly affect object detection model performance, regardless of model architecture. When using object detection mode
arXiv:2609.26103v1 Announce Type: new Abstract: Medical Image Super-Resolution (MISR) aims to enhance spatial resolution without requiring hardware modifications. Although deep learning has yielded pr
arXiv:2609.25611v1 Announce Type: new Abstract: We introduce Qwen3.8-Omni-Flash, a natively multimodal agentic model for real-world multimodal productivity. Compared with previous omni models, which p
arXiv:2609.25602v1 Announce Type: cross Abstract: In language models, the choice between believing the prompt and believing the weights is made by a handful of identifiable attention heads. Instructio
arXiv:2609.25994v1 Announce Type: new Abstract: Providing safe and effective mobility assistance plays a crucial role in restoring independence and enhancing the quality of life for individuals with m
arXiv:2609.22586v1 Announce Type: cross Abstract: Modern audio-language models are no longer judged only on what words they can transcribe, but on whether they can reason over what they hear: recoveri
arXiv:2609.22792v1 Announce Type: cross Abstract: LLM agents are increasingly used for security tasks: vulnerability discovery, exploit reproduction, and patch generation. Improving them at the model
arXiv:2609.25352v1 Announce Type: cross Abstract: Evaluation of large language models (LLMs) for safety, security, and privacy (SSP) relies heavily on static benchmarks, which suffer from score satura
arXiv:2609.24677v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to make predictions from numerical time-series histories and textual events. Yet accuracy alone canno
arXiv:2609.22961v1 Announce Type: cross Abstract: Agentic systems increasingly invoke tools, services, data, and other agents across organizational boundaries, yet a relying party cannot assess a dele
arXiv:2609.23408v1 Announce Type: new Abstract: In frame interpolation tasks, motion ambiguity in the training set causes models to generate blurry intermediate frames. Moreover, the assumption of uni
arXiv:2609.22332v1 Announce Type: cross Abstract: Generalizable robot manipulation requires predicting how a scene will evolve, identifying where interactions are feasible, and determining how to act.
Anthropic says its new Claude Opus 5.5 model comes with stronger safeguards in the wake of recent rogue AI hacking incidents. In an announcement on Tuesday, Anthropic says Opus 5.5 comes with improvem
arXiv:2609.24797v1 Announce Type: new Abstract: Linear RNNs based on the delta-rule enable efficient sequence modeling, but their linear updates with a low-rank correction constrain their expressivity
arXiv:2609.23614v1 Announce Type: new Abstract: Contact-rich manipulation, requiring robots to regulate not only motion but also how they yield to external forces, has emerged as the next frontier for
arXiv:2609.23012v1 Announce Type: new Abstract: Generative vision-language models (VLMs) offer a counting paradigm in which one model produces both a count and a natural-language account of the scene,
arXiv:2609.22471v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models are increasingly deployed alongside Speculative Decoding (SD) to accelerate inference, but combining the two is challe
arXiv:2609.23761v1 Announce Type: new Abstract: Internal voids are ubiquitous defects in manufactured structures, yet their characterization remains challenging because their geometry is hidden and ca
arXiv:2609.22264v1 Announce Type: cross Abstract: State-of-the-art models for audio-driven digital human generation have achieved photo-realistic results in talking-head synthesis. However, extending
arXiv:2609.24033v1 Announce Type: new Abstract: Reliable action evaluation in contact-rich manipulation requires looking beyond the current observation to future visual and contact consequences. Exist
arXiv:2609.22230v1 Announce Type: new Abstract: Counting the items in a bracketed list looks trivial, yet open-weight chat models often get it wrong. Prior work usually blames input bottlenecks such a
Release: llm 0.36 New OpenAI models: gpt-6-sol for GPT-6 Sol and gpt-6-luna for GPT-6 Luna. #1702 Model plugins can now declare supports_conversation = False for models that only accept single-turn pr
arXiv:2609.23935v1 Announce Type: new Abstract: Post-training turns a general next-token predictor into a chat model with a persistent assistant persona. If that persona is a character the model plays