Knowledge catalogue
arXiv:2509.25143v2 Announce Type: replace-cross Abstract: Existing medical reasoning benchmarks for vision-language models primarily focus on analyzing a patient's condition based on an image from a s
arXiv:2608.10932v1 Announce Type: cross Abstract: Understanding camera motion is fundamental to video perception, with applications in spatial intelligence and controllable video generation. Multimoda
arXiv:2608.11191v1 Announce Type: cross Abstract: GUI Visual Grounding is a fundamental capability for GUI agents. Existing models typically freeze their parameters after deployment, limiting their ab
Ran the model with quants (Q5) and MTP by bartowski with llama.cpp server. It takes ~24GB ram running on M5 Pro with 48GB at about 65t/s. On some tasks it was quite the overthinker. Overall, the quali
arXiv:2608.10145v1 Announce Type: new Abstract: LeWorldModel trains a latent world model with a prediction loss and a single anti-collapse regulariser, and reports approximately 87% of goals reached o
arXiv:2505.11635v2 Announce Type: cross Abstract: Many real-world tasks, from associative memory to symbolic reasoning, benefit from discrete, structured representations that standard continuous laten
The model punches above its weight, outperforming Gemma 4 E2B and Ministral 3 3B across a broad range of visual understanding benchmarks and delivers particularly strong results on document understand
The most dangerous document extraction failure isn't a wrong value. It's a missing row that looks like nothing is wrong. We released ExtractBench yesterday: 370 enterprise docs, 14 systems. The hardes
arXiv:2608.09941v1 Announce Type: new Abstract: While 4-bit weight quantization is critical for deploying Small Language Models (SLMs) on edge devices, evaluations of the resulting performance degrada
arXiv:2606.15821v2 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) have produced many specialized multimodal LLMs (MLLMs) that share common foundational LLMs, fo
Today, we’re adding another member to our model family. Meet North Micro Vision. Our smallest vision-language model yet, ideal for sophisticated document understanding. Available open-source under an
arXiv:2608.10268v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly mediate legal determinations over what human rights are realized, and how. Yet, no evaluation benchmark exis
arXiv:2608.10447v1 Announce Type: cross Abstract: Large language model-based recommender systems are increasingly adopting slow-thinking models that generate step-by-step reasoning before making predi
arXiv:2608.10346v1 Announce Type: cross Abstract: Although advancements in face landmark detection (FLD) methods continue to push performance boundaries, they overlook two major functional limitations
arXiv:2608.10176v1 Announce Type: new Abstract: Public service chatbots are expected to deliver recommendations from an underlying public service directory, while also making sure that the recommendat
Try Grok 4.6 on tough real-world tasks! imo GDPVal is probably the most important benchmark, it measures the performance of models on real world tasks Big leap in performance here to top it at a great
Try Qwen-Image-3.0 on @openart_ai! 🎨👀 Qwen Image 3.0 is now on OpenArt ✨ The most Real Qwen image model yet. Native text across 12 languages, precise 10px type, and full interfaces like web pages, gam
arXiv:2608.10007v1 Announce Type: cross Abstract: The current state-of-the-art (SOTA) deep randomized neural networks, such as deep Random Vector Functional Link (dRVFL) and ensemble deep RVFL (edRVFL
arXiv:2608.10042v1 Announce Type: cross Abstract: Tool-use LLMs are increasingly asked to act on users' behalf, but existing benchmarks usually focus on profile recall, style imitation, generic tool u
arXiv:2603.18446v2 Announce Type: replace Abstract: Long-context inference remains challenging for large language models due to attention dilution and out-of-distribution degradation. Context selectio
arXiv:2608.11047v1 Announce Type: new Abstract: While existing benchmarks have made substantial progress in evaluating LLMs across STEM domains, financial reasoning over structured data remains compar
What's Changed Models that don't set a repeat_penalty now default to 1.0 (off) instead of 1.1, matching other engines and speeding up speculative decoding; set a per-model parameter if an older model
arXiv:2608.10875v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly deployed as personal assistants. Existing evaluations, however, mostly use short, self-contained re
arXiv:2608.10408v1 Announce Type: new Abstract: Vision-language models (VLMs) have shown strong capabilities in generating visualization code from textual or visual specifications. However, real-world
arXiv:2607.16173v2 Announce Type: replace Abstract: Open-vocabulary 3D maps let robots answer language queries about what and where, but they assume a static world and cannot answer queries about how
arXiv:2608.10682v1 Announce Type: new Abstract: Single-frame surround-view reconstruction faces severe geometric instability and rendering artifacts due to minimal inter-camera overlap. While existing
arXiv:2608.10359v1 Announce Type: cross Abstract: As information increasingly traverses linguistic boundaries, users require concise cross-lingual representations of long-form content. Nevertheless, l
We are in an insane run of open-weight drops. Every modality, open source is winning. This is what an open source AI summer ☀️ looks like: 🧠 LLMs & Reasoning → DeepSeek-V4-Flash-0731 (my king 👑): 304B
We have her dash camera which shows they are lying. The agents are wearing body cameras and should have dash cameras of their own. If what they say happened was true they wouldn’t be issuing statement
We wrote a 36-page ArXiv whitepaper on ExtractBench 🧑🔬 , our effort to create the most comprehensive, schema-guided, real-world document extraction benchmark. It’s extremely detailed and covers every
Warning: Kinda long post. If you don't like reading, please skip for your own sanity. Also, I've got nothing to sell, just a tinkerer, so I just want to share ideas and learn from you guys too. When I
arXiv:2608.09942v1 Announce Type: cross Abstract: It is widely assumed that chain-of-thought (CoT) prompting universally improves LLM reasoning. We investigate this through the conceptual framework of
arXiv:2608.11024v1 Announce Type: new Abstract: Attribute hallucination---where vision-language models (VLMs) correctly identify an object but mischaracterize its properties---is prevalent yet mechani
arXiv:2608.10220v1 Announce Type: new Abstract: Humanoid locomotion in highly confined environments requires navigating dense environmental obstacles and complex self-collision bounds while maintainin
arXiv:2608.11095v1 Announce Type: new Abstract: Agentic coding READMEs like CLAUDE.md grow without bound in real repositories, stopping only when the repository retires or someone rewrites the file wh
Why does CLAUDE.MD keep growing? If you maintain a CLAUDE.md or an AGENTS.md, this one is worth your time. (bookmark it) This work traces why these files grow without bound. Appending an instruction i
With the smartest person I know, @HarshSensei, we're building evsys-sdk for the community, this open-source repository allows anyone to build their own continual learning system with first-class suppo
arXiv:2608.10279v1 Announce Type: cross Abstract: Streaming language-model output creates a release-timing problem: complete-response moderation acts after streamed text has escaped, whereas repeated
arXiv:2608.11022v1 Announce Type: cross Abstract: Model Cards and Data Cards have demonstrated the value of structured, human-readable documentation for machine learning artifacts, capturing their con
A few things right off the bat: it reasons very efficiently. Like Grok 4.5 levels of efficient thinking it quantizes very well. My first few tests with iq3_xxs were better than Qwen/Gemma behaved at t
Hello everyone! I like dumb things. I like working with weak computers and microcontrollers. I like the simplicity and low electricity usage. Simply put, the efficiency of a 'dumb' PC. The first tim
Seems like we're limited to qwen finetuned MoEs for now. Looking at the current landscape - focus seems to be on dense models (muse glimmer 30b, qwen 3.8 27b) for smaller setups. Is upgrading to 24GB
arXiv:2608.08814v1 Announce Type: cross Abstract: We present 360CityArena, a benchmark for evaluating the urban exploration capabilities of embodied agents within a photorealistic environment construc
⚡️A coalition that secures long-term AI capacity: We’re aggregating long-term compute demand in Europe to determine what capacity is built, where it’s located, and whom it serves. Through these multi-
arXiv:2506.06989v3 Announce Type: replace-cross Abstract: Learning-to-rank (LTR) systems commonly depend on implicit feedback, such as user clicks, because it is easy to collect and can serve as a val
arXiv:2608.08240v1 Announce Type: new Abstract: This paper explores the idea of promoting well-being and safety in human-AI interactions by forcing AI agents explicitly to empower humans and to manage
arXiv:2501.17629v2 Announce Type: replace-cross Abstract: Several studies claim that large language models have passed the Turing Test and hence can 'think', yet none follow Turing's original instruct
arXiv:2608.09004v1 Announce Type: cross Abstract: We prove a sharp lower bound for smooth nonconvex stochastic optimization with uniformly bounded gradient noise. In the (K=1) fresh-sample model, ever
arXiv:2608.09072v1 Announce Type: cross Abstract: Large language model-powered coding agents are increasingly used to modify existing code repositories, for example, by adding features or fixing bugs.
Imagine this scenario: Your team decides to migrate a core application from an existing commercial database like Oracle or SQL Server to open source PostgreSQL or a fully managed service such as Alloy
arXiv:2506.02594v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to synthesize heuristic programs, yet most existing pipelines optimize solvers against fixed benc
arXiv:2608.09476v1 Announce Type: cross Abstract: Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API. We define behavio
arXiv:2607.10180v2 Announce Type: replace-cross Abstract: We introduce ActiveFly-Bench, the first benchmark to bridge cyberspace reasoning and physical-world interaction for UAV embodied perception. T
arXiv:2608.07982v1 Announce Type: new Abstract: Vision foundation models (VFMs) such as DINO are pretrained for single-image representation, whereas remote sensing change detection requires reasoning
arXiv:2608.09789v1 Announce Type: new Abstract: Industrial anomaly detection (IAD) requires identifying fine-grained deviations from normal visual patterns. Multimodal large language models (MLLMs) ca
arXiv:2608.07987v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have demonstrated significant potential in complex spatial scene understanding and reasoning tasks. However, th
arXiv:2608.07636v1 Announce Type: cross Abstract: Deep-OCR (DeepSeek-OCR) advances document recognition by treating the visual modality as an optical compression medium, enabling long-context OCR at l
arXiv:2603.07313v4 Announce Type: replace-cross Abstract: Robustness under latent distribution shift remains challenging in partially observable reinforcement learning. We formalize a focused setting
arXiv:2608.07557v1 Announce Type: cross Abstract: Vision-Language Navigation for Unmanned Aerial Vehicles (UAV-VLN) requires rapid and reactive control in complex 3D environments. Recent minimalist en
arXiv:2608.08874v1 Announce Type: new Abstract: Spoken language offers a natural, hands-free interface for specifying an arbitrary target in dense remote-sensing imagery, yet existing referring remote