Knowledge catalogue
arXiv:2609.07568v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed for translation tasks, yet their implicit political positioning in such contexts remains unders
arXiv:2603.27611v2 Announce Type: replace Abstract: When a cognitive system modifies its own functioning, what exactly does it modify: a low-level rule, a control rule, or the criterion that evaluates
arXiv:2609.05882v1 Announce Type: cross Abstract: Multi-turn interaction creates a feedback process in which an LLM's previous responses become context for later behavior. Prior work shows substantial
arXiv:2609.05531v1 Announce Type: cross Abstract: No specification says how a governed autotelic AI agent organization, where agents pursue self-generated goals inside guardrails, should be designed a
arXiv:2609.09696v1 Announce Type: new Abstract: Large language models are increasingly proposed as automated auditors of document quality, yet their reliability as detectors of planted errors is poorl
arXiv:2609.09684v1 Announce Type: new Abstract: Medical question-answering datasets often contain answer labels, whereas high-quality rationales remain scarce, noisy, or costly to validate. This chang
arXiv:2510.15047v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) as agents often fail to improve in new environments. We identify and characterize a failure mode we call explorat
arXiv:2609.08224v1 Announce Type: new Abstract: Intermediate representations are key to bridging the modality gap between generalizable manipulation policies and large-scale pretrained vision-language
arXiv:2609.05435v1 Announce Type: new Abstract: Modern language agents are expected to operate over long horizons: they ask follow-up questions, reuse worked examples, handle tool feedback, and adapt
arXiv:2609.06991v1 Announce Type: new Abstract: Recent text-to-audio-video (T2AV) models jointly generate video, speech, sound effects, and ambience from a single text prompt. This capability poses ne
arXiv:2609.07720v1 Announce Type: new Abstract: Long-form narrative-to-film generation requires shot-level controllability and cross-clip consistency in both visual identity and character behavior-req
arXiv:2609.05730v1 Announce Type: new Abstract: Contrastive Language-Image Pretraining (CLIP) is a building block of many machine learning applications. Scaling laws have guided resource allocation fo
arXiv:2404.06349v3 Announce Type: replace Abstract: The ability to understand causality significantly impacts the competence of large language models (LLMs) in output explanation and counterfactual re
arXiv:2609.07004v1 Announce Type: new Abstract: Accurate segmentation of pulmonary lesions is essential for effective clinical diagnosis and treatment strategies. Existing segmentation approaches ofte
arXiv:2609.08657v1 Announce Type: new Abstract: Charts are structured visual compositions whose elements have distinct functional roles, semantic correspondences, and visibility relations. This struct
arXiv:2609.07110v1 Announce Type: new Abstract: Natural adversarial examples (NAEs) reveal that vision models can fail under realistic semantic changes beyond norm-bounded perturbations. However, gene
arXiv:2609.09004v1 Announce Type: cross Abstract: Large Language Models (LLMs) demonstrate impressive performance across diverse NLP tasks, yet their ability to exhibit genuine contextual understandin
arXiv:2609.07403v1 Announce Type: new Abstract: Privacy-sensitive surveillance systems could benefit from large vision-language models (VLMs), but such models typically require centralized access to r
arXiv:2609.08848v1 Announce Type: new Abstract: We present FIRE3D, a unified framework that takes a single RGB image or casual RGB video and transforms it into simulation-ready 3D scene assets for gam
arXiv:2609.08886v1 Announce Type: new Abstract: Language-guided robots need persistent scene memories to follow instructions, revisit objects, and resolve references to objects encountered over time.
arXiv:2609.08391v1 Announce Type: new Abstract: Remote sensing multimodal large language models (RS-MLLMs) have advanced scene understanding and visual question answering over satellite imagery, yet l
arXiv:2609.06058v1 Announce Type: new Abstract: As vision-language models (VLMs) become increasingly capable and are deployed in consequential real-world settings, they must evaluate evidence independ
arXiv:2609.07091v1 Announce Type: new Abstract: Autonomous mobile robots performing person-following tasks often suffer from temporary occlusions and sensor track loss in dynamic environments. This re
arXiv:2609.05946v1 Announce Type: new Abstract: Interpretability and fairness are two of the most emphasized dimensions in trustworthy artificial intelligence (AI). Various explainable AI methods have
arXiv:2505.17966v3 Announce Type: replace-cross Abstract: This paper evaluates single-view mesh reconstruction models for their potential in enabling instant digital twin creation for real-time planni
arXiv:2509.04772v2 Announce Type: replace Abstract: Timely floodwater depth estimates support road accessibility assessment and emergency response during urban flooding. Supervised vision methods ofte
arXiv:2606.19706v2 Announce Type: replace Abstract: Recent progress in vision-language models has enabled processing of increasingly long video sequences, but handling extended token streams does not
Nice paper to improve inference efficiency. It's been a while we haven't seen good work on efficiency. Here is why it matters: A long-running agent's workspace outgrows its context window long before
arXiv:2602.00110v2 Announce Type: replace Abstract: Visual transformers have driven major progress in remote sensing image analysis, particularly in object detection and segmentation. Recent vision-la
arXiv:2609.06810v1 Announce Type: new Abstract: Optical coherence tomography (OCT) offers compact, contactless, micron-scale imaging suitable for intraoperative guidance, but native OCT volumes are di
arXiv:2609.08215v1 Announce Type: new Abstract: Video generation models have recently attracted substantial attention for their ability to generate visually compelling videos, yet ensuring physically
arXiv:2609.07916v1 Announce Type: new Abstract: Images are important tools in various sciences. Despite the development of photo-taking tools, creating clear and image without noise remains challengin
arXiv:2104.00239v3 Announce Type: replace Abstract: Visual and audio signals often coexist in natural environments, forming audio-visual events (AVEs). Given a video, we aim to localize video segments
arXiv:2609.05953v1 Announce Type: new Abstract: Few-shot fine-grained object detection (FGOD) in remote sensing imagery is challenging because limited annotations must support both object localization
Model available here: Qwen3.8-27B-Uncensored-Genesis-V1-MTP-GGUF This model is a practical realisation of things described in this paper, but adapted by me for machine learning: https://arxiv.org/pdf/
arXiv:2512.23243v3 Announce Type: replace Abstract: Multimodal vision-language modeling has emerged as a promising paradigm for remote sensing (RS) image understanding. However, existing methods are l
arXiv:2609.07941v1 Announce Type: new Abstract: In this paper, we propose ReactVAU, a Slow-Fast Decoupled Framework for real-time streaming Video Anomaly Understanding (VAU). Existing VAU methods rely
arXiv:2505.01862v4 Announce Type: replace Abstract: Adapting autonomous agents for real-world industrial, domestic, and other daily tasks is currently gaining momentum. However, in global or cross-lin
arXiv:2609.06078v1 Announce Type: new Abstract: This report summarizes the 8th Large-scale Video Object Segmentation (LSVOS) Challenge, held in conjunction with ECCV 2026. The challenge evaluates vide
arXiv:2609.06530v1 Announce Type: new Abstract: Continual learning is a crucial capability for Graphical User Interface (GUI) agents to adapt to evolving applications while retaining knowledge acquire
arXiv:2609.06473v1 Announce Type: new Abstract: Inference-time activation steering enables behavioral control of large language models without parameter modification, while post-training quantization
arXiv:2609.05596v1 Announce Type: new Abstract: Can interactive vision-and-language agents learn not just what to say but also extbf{extit{when}} to say it? Current language models rarely plan over wh
arXiv:2609.06100v1 Announce Type: new Abstract: Verifiable outcome rewards guide language-model post-training, but sequence-level advantages do not identify which token-level decisions should be prese
arXiv:2609.08040v1 Announce Type: cross Abstract: The software supply chain has become an increasingly exposed attack surface because of its reliance on intricate yet fragile dependencies. Existing de
arXiv:2606.14787v2 Announce Type: replace Abstract: We study six production image-to-image AI systems (gpt-image-1, Gemini 2.5 Flash Image, Flux Kontext, SDXL img2img, SD3 img2img, and Qwen Image Edit
arXiv:2609.07313v1 Announce Type: cross Abstract: Segmentation of complex structures in X-ray tomographic data is a fundamental task in biomedical research, but it often requires large amounts of prec
We're introducing Q2D-Web (Query2Doc-Web), a benchmark and public leaderboard for evaluating retrieval in agentic RAG systems. Q2D-Web tests how embedding models perform on large-scale web search usin
What is Astra actually supposed to be better at, Because if the answer is “everything,” then I genuinely do not understand what kind of testing was done for writing-heavy use cases. My biggest issue i
I was reading up on the recent controversy around Tristan Buckmaster, Levent Alpöge, OpenAI, and the Navier–Stokes result, and it got me thinking about something broader than this particular dispute.
We have just raised 3B€ to accelerate our R&D. We are scaling up our training and inference compute to build future generations of our models, and expanding our Science team across all our offices --
I’ve been thinking about this after using more agentic/local coding models. A lot of the newer models are surprisingly good at continuing on their own. But sometimes that seems like the problem. If a
arXiv:2609.04539v1 Announce Type: new Abstract: A critical challenge in deploying Large Language Models (LLMs) is developing reliable mechanisms to estimate their confidence, enabling systems to deter
arXiv:2609.04807v1 Announce Type: cross Abstract: Multi-vehicle cooperative autonomous driving enhances the safety and reliability of autonomous driving systems through information sharing among conne
What can I do to get more from MTP if anything? It am I sitting at the expected range. Thanks /opt/llama.cpp/build/bin/llama-server --host 10.210.44.126 --port 11434 --model /opt/models/Qwen3.6-35B-A3
arXiv:2609.05149v1 Announce Type: new Abstract: Vision-Language Models are commonly evaluated through their final predictions, but understanding whether these decisions are grounded in visual evidence
arXiv:2609.05025v1 Announce Type: cross Abstract: Hallucination-where a language model generates outputs that are factually incorrect or unsupported by the source-is a major challenge for both prompte
arXiv:2609.05178v1 Announce Type: new Abstract: Vision-Language-Action (VLA) or World Action (WAM) models have recently demonstrated remarkable performance in robotic manipulation. On LIBERO, SOTA met
Hi, I use hermes as a harness, and I am pleased with it, but sometimes Hermes's context size is a bit too much for my system, so I wanted to delegate or straight up use a lighter option for coding tas
One thing that has bothered me about LLM benchmarks for a while is that most of them are essentially snapshots. A model is evaluated, a score is published, and we tend to talk about that score as if i
arXiv:2609.04835v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used not only to retrieve information, but to answer questions, explain, teach, and support inquiry. In su