Knowledge catalogue
llama: share the nextn tensor flags between models Follow-up of the TODO in glm5-next: move the trunk-only and MTP-only detection that each model copied into a nextn_flags helper of llama_model_base.
Banger paper from NVIDIA. One exciting trend I am seeing is building verifiable environments for your agents and training the harness alongside the model. Co-evolving the harness and the model is a bi
arXiv:2610.07417v1 Announce Type: cross Abstract: Bayesian Optimization (BO) has become an established methodology for minimizing black-box functions of a vector input. Often, however, this parameter
arXiv:2610.07056v1 Announce Type: cross Abstract: Behavioral cloning (BC), despite its simplicity, exhibits many counterintuitive phenomena in the real world. For example, the performance of BC often
arXiv:2610.07674v1 Announce Type: cross Abstract: Controlling a hybrid system to a target set under parameter uncertainty can require informative actions that temporarily drive the system state away f
arXiv:2610.07420v1 Announce Type: new Abstract: Electroencephalography (EEG) signals drift over time, which can cause static brain-computer interface (BCI) models to degrade in practice. We present a
arXiv:2610.07232v1 Announce Type: new Abstract: Accurate short-term load forecasting (STLF) is essential for the reliable and efficient operation of modern power systems. While time series foundation
arXiv:2610.08101v1 Announce Type: new Abstract: Shared memory coordinates agents' actions, but correct records do not establish that those actions satisfy task requirements. Memory governance and fail
arXiv:2610.08132v1 Announce Type: cross Abstract: Concept drift threatens production machine learning, yet the empirical behavior of multivariate two-sample drift detectors at scale remains under-char
arXiv:2603.15822v2 Announce Type: replace Abstract: Automated radiology report generation from 3D CT volumes often suffers from incomplete pathology coverage. We provide empirical evidence that this l
arXiv:2610.08173v1 Announce Type: cross Abstract: Automated Program Repair (APR) with language models is usually evaluated by whether a generated patch passes the test suite, which can hide difference
arXiv:2610.08109v1 Announce Type: new Abstract: Cardiac magnetic resonance imaging reconstruction aims to recover high-quality images from undersampled acquisitions, enabling faster scans while preser
arXiv:2610.07594v1 Announce Type: cross Abstract: Humanoid household manipulation requires the arms to act while the body balances, steps and changes posture. We present BiGym 2.0, an adaptation of Bi
arXiv:2610.07614v1 Announce Type: new Abstract: We evaluate whether AI agents can match the reported findings of published biomedical studies using public data. Existing evaluations do not consistentl
arXiv:2610.07686v1 Announce Type: new Abstract: We introduce BluffJAX: an open-source suite of adversarial imperfect information games in JAX. We provide canonical implementations of games designed fo
arXiv:2610.06972v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in visual understanding and multimodal reasoning, yet they remain fun
arXiv:2610.07668v1 Announce Type: cross Abstract: Modern cache replacement designs saturate because they operate within fixed representational structures, hand-crafted and heuristic based feature-engi
arXiv:2610.07019v1 Announce Type: new Abstract: Fiorillo v0.5 is an open model that answers typed questions with a probability for each answer. Its main specialist reads a randomized trial's article,
arXiv:2610.07219v1 Announce Type: new Abstract: Mixture-of-experts models make nearly trillion-parameter capacity accessible with sparse per-token computation, provided that the serving system can dis
arXiv:2610.07939v1 Announce Type: new Abstract: Due to rapid advances in Generative AI, commercial video generation tools can be used to produce fabricated surveillance footage that can fool both huma
arXiv:2610.08106v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) advance rapidly, while conventional benchmark development lags behind, delaying investigation of newly observed
arXiv:2610.07557v1 Announce Type: cross Abstract: Static-analysis checker synthesis requires agents to interpret a defect specification, inspect a repository, implement analyzer-specific logic, and re
Claude Haiku 5.5 is now available on OpenDocRouter as one of the cheapest models for document parsing. It is roughly $1.2 / 1k pages and does quite well on tables and text reading order compared to ot
arXiv:2610.08457v1 Announce Type: new Abstract: Integrated circuit design involves multiple design stages: logic synthesis, floorplanning, placement, and routing, with each stage taking hours to weeks
arXiv:2610.07177v1 Announce Type: cross Abstract: An open contrastive decision model is near chance as a judge on the hard public benchmarks: Contrastive-LM/CLM-v0.1-8B scores between 0.351 (best- of-
arXiv:2610.08592v1 Announce Type: new Abstract: CNet is a C++/CUDA framework for building and training deep complex-valued neural networks (CVNNs) and, more generally, for optimizing complex-valued fu
arXiv:2610.08312v1 Announce Type: new Abstract: Continual learning (CL) is essential for Large Language Models (LLMs) to sequentially adapt to evolving tasks. To mitigate catastrophic forgetting, rece
arXiv:2610.08183v1 Announce Type: cross Abstract: Multi-task manipulation policies differ in architecture, scale, and pretrained priors all at once, so published comparisons cannot attribute performan
arXiv:2610.07761v1 Announce Type: cross Abstract: In this work, we propose a novel recommendation model, CLARER (Contrastive Learning for Aspect Representation towards Explainable Recommendation) that
OpenAI introduced interactive in‑chat tools that let users play games or run utility calculators—such as an interactive budget planner—directly within a conversation. The demonstration, released on Oc
arXiv:2610.07132v1 Announce Type: cross Abstract: Croissant has emerged as a standard for machine-readable dataset metadata, yet populating its fields remains labor-intensive and requires careful read
https://preview.redd.it/owhrvbbiu2uh1.png?width=4096&format=png&auto=webp&s=55d816753e7adee0e1391c9f581052b4bde44da7 d1-omni-600M d1-omni-600M is a 600M parameter decision model built on LFM2.5-Encode
arXiv:2610.08048v1 Announce Type: new Abstract: LLM agents often lack the operational knowledge to act reliably in new environments, as they must discover specific tool behaviors or environment conven
arXiv:2610.06993v1 Announce Type: cross Abstract: Evolution Strategies (ES) enable memory efficient full parameter fine-tuning of large language models (LLMs) using only forward computation. However,
arXiv:2610.07967v1 Announce Type: new Abstract: As large language model (LLM) agents become increasingly autonomous, they may pursue task performance through deception, raising concerns about their re
On 15 September, TypeSafe released Jev, and within a few weeks about 10 companies had shipped something that works the same way. OpenAI, Liquid, Cloudflare, AWS and PostHog all launched one, and an op
OpenAI’s tweet (posted Oct 7 2026 at 6:05 PM) promotes the idea that visual content can deepen comprehension of a topic, highlighting how images make concepts “come to life.” The post, part of OpenAI’
arXiv:2610.07403v1 Announce Type: new Abstract: Long-term memory allows Large Language Models (LLMs) to maintain personalized context across interactions, but retrieved user history can induce memory-
arXiv:2610.08738v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) hold the promise of order-agnostic, parallel text generation. Recently, continuous diffusion and flow matching models h
arXiv:2610.08341v1 Announce Type: new Abstract: Recent training-free pruning approaches for Multimodal Large Language Models (MLLMs) effectively cut computational overhead by exploiting visual redunda
arXiv:2610.06921v1 Announce Type: new Abstract: Before deploying runtime recovery for a frozen vision-language-action (VLA) policy, one must establish that an intervention improves success beyond ordi
arXiv:2610.07722v1 Announce Type: new Abstract: Activation steering provides a lightweight and flexible way to control large language model (LLM) behavior. However, effective steering requires more th
arXiv:2610.07270v1 Announce Type: new Abstract: Internal features in LLMs are often interpreted as mechanisms when they track a concept and their manipulation changes a related behavior. Yet steering
arXiv:2610.08102v1 Announce Type: new Abstract: Conversational MLLM agents are increasingly expected to assist in professional workflows, from AI research and engineering design to product management
arXiv:2610.07014v1 Announce Type: new Abstract: RGB-D semantic segmentation has made notable progress by fusing RGB and Depth, yet mainstream models still learn features almost exclusively from pixel-
arXiv:2610.07928v1 Announce Type: cross Abstract: Dynamic multimodal learning aims to learn robust representations by adaptively modeling information discrepancies across modalities. However, existing
arXiv:2610.07362v1 Announce Type: new Abstract: We evaluate large language models (LLMs) in multi-turn interactions through their time-to-event: the number of interaction steps required to produce an
arXiv:2610.07848v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) has become a standard approach for adapting large language models to downstream tasks. However, most existing P
arXiv:2610.06885v1 Announce Type: cross Abstract: Moving target defense (MTD) against advanced persistent threats (APTs) in industrial control systems (ICS) has well-established game-theoretic formula
arXiv:2610.07456v1 Announce Type: new Abstract: A common assumption to simplify the problem of controlling a multi-UAV slung load system (MUSLS) is that the flexible cables can be modeled as massless
arXiv:2610.08624v1 Announce Type: cross Abstract: We propose a method for choosing the shared memory parameter eta_1=eta_2=eta in Adam from a short pilot training. The selected eta remains fixed durin
Grace Kay / The Information: Elon Musk says Grok Bot will use the “best back end model for any given task, including Claude Opus 5.5, MidJourney, Suno” — Elon Musk announced on Tuesday night that Spac
arXiv:2610.08432v1 Announce Type: new Abstract: Improving embodied agents often focuses on optimizing the underlying model through training, while the surrounding agent harness that controls planning,
arXiv:2610.06956v1 Announce Type: new Abstract: Large speech language models have demonstrated strong capabilities in unified cross-modal understanding and generation, yet paralinguistic cues, especia
arXiv:2610.08108v1 Announce Type: new Abstract: Diffusion language models (dLLMs) have emerged as a promising alternative to autoregressive (AR) language models, offering flexible token-update orders
arXiv:2610.06986v1 Announce Type: new Abstract: AI research agents are increasingly used to search over programs, mathematical constructions, and proofs. However, existing systems typically optimize e
arXiv:2610.07345v1 Announce Type: cross Abstract: IAM policy analysis typically emphasizes the authorization capabilities encoded in a policy, but security analyst review priority may also depend on t
arXiv:2610.07354v1 Announce Type: new Abstract: Deciding when to escalate a query from a small language model to a larger one requires a cheap signal that predicts, before the large model is called, w
arXiv:2610.07094v1 Announce Type: cross Abstract: LLM deployment is shifting from single-turn completion to agentic trajectories in which a model plans, calls tools, reads results and reasons at test
arXiv:2504.18225v2 Announce Type: replace Abstract: We introduce a new generation of small reasoning models for RAG, search, and source summarization. Pleias-RAG-350m and Pleias-RAG-1B are mid-trained