Knowledge catalogue
arXiv:2609.29233v1 Announce Type: cross Abstract: We find that language models can transfer capabilities through task-unrelated text. Post-training typically improves language models using task-specif
arXiv:2609.29718v1 Announce Type: cross Abstract: Coding agents are beginning to act in the visual world. They now build webpages, GUIs, games, 3D scenes, diagrams, and documents. Success in such visu
arXiv:2609.29458v1 Announce Type: new Abstract: We present a tightened convergence analysis of clipped gradient descent on (L_0, L_1)-smooth functions, with quantitative constants. Building on the ide
arXiv:2609.29183v1 Announce Type: new Abstract: Some documents that embedding-based topic models initially classify as noise later become founding members of emerging topics. At publication time, howe
arXiv:2609.29690v1 Announce Type: new Abstract: University students experience disproportionately high rates of common mental health conditions, such as depression, which can impair learning, social f
arXiv:2609.29775v1 Announce Type: cross Abstract: Large Language Models (LLMs) consume and produce a single sequence of text; hence, if text can be added to the beginning of the LLM's response, i.e.,
arXiv:2609.30094v1 Announce Type: new Abstract: Large language models increasingly operate as persistent assistants in user-facing, shared-session, and tool-augmented settings. When users disclose sen
arXiv:2609.28693v1 Announce Type: new Abstract: Large Language Model (LLM) agents struggle to scale safely when exposed to vast enterprise toolsets. Providing an agent with access to every internal to
arXiv:2609.29504v1 Announce Type: cross Abstract: Aggregate factuality scores hide where a language model succeeds, which relations it confuses, and whether an answer survives innocuous changes to the
arXiv:2609.29604v1 Announce Type: new Abstract: In medical visual question answering (VQA), hallucinations of vision-language models (VLMs) may lead to confident but incorrect responses, raising the r
Prefill step size affects both PP performance and your drafter fetching logits for MTP (affects dflash as well, mlx-vlm needs to be patched slightly to support chunked prefill for dflash). It also nee
arXiv:2609.28727v1 Announce Type: new Abstract: Contextual biasing improves rare-word recognition in speech large language models (SpeechLLMs), but efficiently exploiting large bias lists remains chal
arXiv:2609.29837v1 Announce Type: new Abstract: We introduce PUBG Ally, an embodied agent for PUBG: BATTLEGROUNDS that can reason, act autonomously, and play alongside players as a voice-enabled teamm
arXiv:2609.29276v1 Announce Type: new Abstract: Lexical borrowings are words from one language that are introduced into another language. Identifying lexical borrowings in text is a relevant task for
arXiv:2609.29592v1 Announce Type: cross Abstract: Adapting large pretrained vision models under limited data and frozen-backbone constraints remains a central challenge in transfer learning. While lig
arXiv:2602.06699v2 Announce Type: replace-cross Abstract: We propose a variational quantum implementation of self-attention (QSA)-the core operation in transformers and large language models-which pre
Muse is getting a lot of attention — including mine — because it’s both groundbreaking technically (each user gets their own entire persistent Linux VM running in Meta’s cloud) and because it’s packag
arXiv:2609.29892v1 Announce Type: new Abstract: The rapid progression of large language models is extending AI from passive content generation into the active workflows of engineering and scientific d
Since my last post, I've been thinking about different options for dynamic performance degradation, trying to squeeze as much high-quality inference out of my GPU as I can. Over the weekend I read thi
I’ve been experimenting with whether Qwen3.8-Flash-Next’s pretrained PLE n-gram memory can improve a much smaller Qwen3.5-0.8B model. I trained the 0.8B setup with limited resources, mostly using free
arXiv:2609.30100v1 Announce Type: cross Abstract: Recent advances in paraphrase detection reveal a fundamental trade-off: large language models achieve high accuracy but require high computation, whil
arXiv:2609.29394v1 Announce Type: new Abstract: General-purpose robot agents must learn from experience, transfer to new tasks, and act efficiently. Code as Policies (CaP) methods generate and repair
arXiv:2609.28480v1 Announce Type: cross Abstract: Governments increasingly meet citizens through an AI system rather than a website. RADAR (Readiness for AI Discovery and Agentic Reach) measures wheth
Louise Lucas / Financial Times: Radical Ventures: AI neolabs, many lacking products, markets, or revenue, raised $24B in the past two quarters, nearly 5x OpenAI and Anthropic pre-ChatGPT — It is true
arXiv:2609.30249v1 Announce Type: cross Abstract: Coding agents have demonstrated enormous success in solving complex programming problems. To leverage their potential for robot systems, this work int
arXiv:2609.29714v1 Announce Type: cross Abstract: The complexity of time-domain simulation of modern power systems has increased significantly because converter-based resources introduce control dynam
arXiv:2609.29403v1 Announce Type: new Abstract: Learning surrogates for time-dependent partial differential equations often requires a new simulation corpus when the governing operator changes. We int
arXiv:2609.30079v1 Announce Type: cross Abstract: Graph neural networks (GNNs) have become a prominent approach for developing fast, topology-aware surrogates in electric power systems, supporting tas
arXiv:2609.30082v1 Announce Type: new Abstract: Robust dexterous grasping requires maintaining physical stability despite contacts interactively evolving across the entire hand. A precomputed force di
arXiv:2609.29278v1 Announce Type: cross Abstract: Chain-of-thought (CoT) instructions can distort multiple-choice VLM evaluation when a scorer appends a reasoning cue but reads answer-label logits bef
arXiv:2609.29678v1 Announce Type: cross Abstract: Semi-supervised fine-grained visual recognition is highly vulnerable to overconfident pseudo-label errors: visually similar categories frequently prod
arXiv:2609.28850v1 Announce Type: new Abstract: Reproducing a machine learning paper involves most research steps, from installing software and debugging to running experiments, work that AI agents in
Recommended benchmark. I expect voice to become one of the main ways people interact with robots and physical AI. That makes speech recognition in real conversations much more important than it seems
arXiv:2402.10149v3 Announce Type: cross Abstract: In collider experiments, the kinematic reconstruction of heavy, short-lived particles is vital for precision tests of the Standard Model and in search
arXiv:2609.29151v1 Announce Type: new Abstract: Earth-observation (EO) foundation models provide reusable embeddings, yet downstream task accuracy does not reveal whether these representations encode
arXiv:2609.26176v2 Announce Type: replace-cross Abstract: Encoded-prompt attacks are evaluated almost entirely on their harmful arm: a benchmark sends obfuscated harmful requests and reports how often
arXiv:2609.28765v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) performs well on problems with clear rewards, such as mathematics and coding, but whether it also
Reliable, fast inference is essential. As Ted shared at Apsara Conference 2026, Together makes it easy for teams to get access to frontier open models without needing to manage any of the infrastructu
Remember October 2022 when you doused Galactica with vitriol? Galactica was a 120b-parameter LLM-based system from Meta-FAIR designed to help scientist write papers. It was open sourced (link below).
arXiv:2609.29171v1 Announce Type: cross Abstract: We propose the Representation World Model (RWM), which learns states, transitions, and executable plans directly in representation space. Unlike exist
arXiv:2609.30219v1 Announce Type: cross Abstract: An acceptance protocol is developed for sensor-coordinate and polarity binding in mechatronic commissioning. Candidate generation is separated from re
arXiv:2609.30023v1 Announce Type: new Abstract: Imitation learning enables robots to acquire manipulation skills from demonstrations, but the resulting policies can fail outside the training data, whi
Dylan Freedman / New York Times: Researchers add details to the Hugging Face incident, including OpenAI agents creating ~1M shortened URLs to encode information in an attempt to solve CAPTCHAs — A new
arXiv:2609.30085v1 Announce Type: new Abstract: In multi-target regression, correlated targets are often coupled through multi-output Gaussian processes with an intrinsic model of coregionalisation (G
arXiv:2609.28935v1 Announce Type: new Abstract: Vibrational spectral prediction can become inaccurate when localized stereoelectronic environments perturb intermediate response states and high-risk re
arXiv:2609.29835v1 Announce Type: new Abstract: LiDAR provides precise geometric information for spatial perception tasks such as object detection in autonomous driving and outdoor robotics. However,
arXiv:2609.30087v1 Announce Type: new Abstract: We consider the decision of whether to return an existing draft answer or revise it using retrieved evidence, as in answer-revision systems. Draft confi
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:2609.30213v1 Announce Type: new Abstract: Robots often must satisfy one or more constraints during motion planning for real-world tasks. When such constraints reduce the valid configuration spac
arXiv:2609.28976v1 Announce Type: new Abstract: Visual Navigation Models (VNMs) enable robots to navigate from egocentric visual observations without geometric localization and planning, but long-rang
arXiv:2609.28614v1 Announce Type: new Abstract: Autonomous research agents can design experiments, evaluate results, and write reports, giving them control over both a scientific result and the eviden
arXiv:2609.28778v1 Announce Type: cross Abstract: Audio-language models (ALMs) can exploit textual shortcuts to answer questions while overlooking acoustic evidence, weakening audio understanding. On-
arXiv:2609.29028v1 Announce Type: new Abstract: In this paper, we propose RGBD20K, a novel dataset for facilitating the development of more robust and general RGB-D semantic segmentation by encompassi
arXiv:2609.29181v1 Announce Type: new Abstract: There are many complex issues in the world of artificial intelligence. Some of these problems are solved using other artificial intelligence methods, wh
arXiv:2609.28625v1 Announce Type: new Abstract: Despite the importance of reinforcement learning with verifiable rewards (RLVR), the extent to which it can learn new reasoning capabilities remains deb
arXiv:2609.29389v1 Announce Type: new Abstract: Foundation vision-language models (VLMs) understand objects, instructions, and spatial relations, yet translating this capability into robotic manipulat
arXiv:2609.29490v1 Announce Type: cross Abstract: Recent advances in robotics highlight hierarchical configurations of robot morphology, where multiple levels of functional substructures synergize to
arXiv:2609.28952v1 Announce Type: new Abstract: Robot-policy benchmarks increasingly cover diverse tasks and preset out-of-distribution conditions, but typically evaluate complete trajectories from pr
arXiv:2609.28910v1 Announce Type: cross Abstract: Effective robot assistance beyond narrow roles and repetitive tasks requires robots to be proactive - to decide what needs to be done rather than wait
arXiv:2609.29935v1 Announce Type: cross Abstract: We study the detection of LLM-generated text under editing and contamination. Modeling human and machine text as finite-order Markov processes with Hu