Knowledge catalogue
Qwen3.6-27b is fantastic! It makes me wonder if there's a hard ceiling to smaller sized models. Do you guys think the ceiling of intelligence for smaller models will be constrained by factors like par
arXiv:2607.21267v1 Announce Type: new Abstract: Comprehensive basketball video understanding requires resolving not only what event occurs, but also who is responsible and when the key evidence appear
arXiv:2607.21125v1 Announce Type: new Abstract: Image restoration agents have recently emerged as a flexible paradigm for handling diverse and unpredictable degradations in real-world scenarios. Exist
arXiv:2607.20560v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems retrieve and integrate external knowledge to ground large language model (LLM) outputs. However, current RA
arXiv:2607.20526v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in settings where fluent but incorrect answers can be costly. In these settings, accuracy alone i
arXiv:2607.20462v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into clinical workflows, stressing the need for reliable traceability of model-generated output
When we introduced the Open Knowledge Format (OKF) in June 2026, we asserted that the context that agents need (table schemas, metric definitions, runbooks) should live in a format, not in a proprieta
arXiv:2607.21063v1 Announce Type: new Abstract: Almost every large language model that reaches a broad audience is quantized: trained in full precision, then compressed for efficiency. This step is as
arXiv:2607.21090v1 Announce Type: cross Abstract: We propose a Reinforcement Learning (RL) method to directly optimize the faithfulness of self-explanations - the extent to which a model's generated r
arXiv:2607.20474v1 Announce Type: new Abstract: Natural language interfaces can greatly benefit the accessibility and usability of optimization modeling, and recent advances in large language models (
arXiv:2607.19742v1 Announce Type: cross Abstract: Cyber Threat Intelligence (CTI) reports richly describe real-world attack processes, but their unstructured narratives cannot be directly used for aut
arXiv:2607.09988v3 Announce Type: replace-cross Abstract: Recommendation systems, from traditional multi-stage to recent unified generative architectures, face challenges in incorporating diverse cont
I wanted to know how cheap you can go and still run local models, so I ran Ollama CPU-only on a Youyeetoo X1S. It's a single-board x86 machine with a Celeron N5095 (Jasper Lake, 4C/4T, 15W), 16GB of R
TLDR: I (with the help of AI) re-implemented every Blackwell-only kernel (DeepGEMM, FlashInfer sparse-MLA, block-scaled FP8) in Triton, because they simply don't exist for sm89. The performance is 2-3
arXiv:2607.18510v1 Announce Type: new Abstract: Diffusion Transformers achieve strong image generation performance, but most operate in compressed latent spaces. Pixel-space diffusion avoids this info
The interesting finding from a new [arXiv paper](https://arxiv.org/abs/2607.16165) isn't that a frontier vision model failed a new benchmark, that happens weekly, but the specific shape of the failure
arXiv:2607.18325v1 Announce Type: new Abstract: Modern safety-critical systems increasingly rely on human-robot interaction to reduce disaster risk and support decision-making during emergencies. Visi
Kimi K3 is coming to Together AI on day zero, July 27. Start building with it the moment it launches, powered by Together AI inference for coding, agents, and production workloads. https://www.togethe
arXiv:2607.19365v1 Announce Type: new Abstract: When Large Language Models (LLMs) are used for semantic data extraction from unstructured text, producing candidate relational facts from natural langua
arXiv:2607.18673v2 Announce Type: new Abstract: Vision Language Models (VLMs) are well known for hallucinating non-existent objects in images. Objects with missing parts present a unique challenge for
arXiv:2607.19935v1 Announce Type: new Abstract: Large metal-organic framework (MOF) databases support simulation, screening, and machine learning through crystallographic information files (CIFs). Sub
arXiv:2607.19910v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly expected to automate visualization development by generating code directly from visual designs
arXiv:2607.19405v1 Announce Type: new Abstract: The CoTFormer architecture formalizes Chain-of-Thought as a form of recurrent latent computation, preserving intermediate states as attendable represent
arXiv:2607.19824v1 Announce Type: new Abstract: LLM preference alignment aims to optimize models toward human preferences across diverse user instructions. Reinforcement learning has become a major po
arXiv:2607.18709v2 Announce Type: replace Abstract: Existing robot datasets remain expensive to curate, embodiment-specific, and insufficiently annotated with the fine-grained structure required for g
arXiv:2607.19604v1 Announce Type: new Abstract: Injecting factual knowledge into large language models (LLMs) reliably and at scale remains an open challenge. Hypernetworks provide a promising solutio
arXiv:2607.19850v1 Announce Type: new Abstract: Vision-language models have shown strong potential for social robot navigation by leveraging rich semantic understanding of complex environments and hum
arXiv:2512.03854v2 Announce Type: replace Abstract: Artificial intelligence (AI) is increasingly used in digital pathology. Publicly available histopathology datasets remain scarce, and those that do
What’s one of the biggest bottlenecks stopping organizations from scaling their AI initiatives? It isn’t the capabilities of today’s models — it’s their access to business context and semantic meaning
i used to do this a lot. but then i felt like i was getting progressively dumber at writing. i think there's some value in forcing your own brain to sharpen your thinking, instead of offloading it to
We benchmarked Gemini 3.6 Flash and Gemini 3.5 Flash Lite on document understanding. We compared against their prior versions - Gemini 3.5 Flash and Gemini 3.1 Flash Lite. 1️⃣ Gemini 3.6 Flash has rou
This is what strong inference economics unlock. @rox_ai built its own search agent, ran it in production for 6+ months, and reached 91.3% accuracy at 1.03¢ per query. Together AI is proud to help powe
// Global Workspace in LLMs // arXiv paper for the popular J-space work from Anthropic. (bookmark it) The short recap: If you build on chain-of-thought or steering vectors, this work provides a mechan
Long-running models can solve hard open-ended problems, but their persistence can create safety risks that shorter-horizon evaluations miss. We’re sharing what we learned from studying a long-running
arXiv:2606.16944v2 Announce Type: replace Abstract: Theory of mind (ToM), the capacity to ascribe mental states to others and use those ascriptions for prediction and inference, is widely assumed to b
arXiv:2601.22830v2 Announce Type: replace Abstract: Reliable environmental perception remains one of the main obstacles for safe operation of automated vehicles. Safety of the Intended Functionality (
arXiv:2507.19593v3 Announce Type: replace Abstract: Classical game-theoretic models typically assume rational agents, complete information, and common knowledge of payoffs - assumptions that are often
arXiv:2603.00546v2 Announce Type: replace Abstract: Using Multimodal Large Language Models (MLLMs) as judges to achieve precise and consistent evaluations has gradually become an emerging paradigm acr
arXiv:2511.18685v4 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) show promising results as decision-making engines for embodied agents operating in complex, physical enviro
arXiv:2607.13216v1 Announce Type: cross Abstract: Humans recognize movements effortlessly, even from noisy and complex visual input. But what information in the stimulus allows humans to rapidly class
arXiv:2607.13399v1 Announce Type: cross Abstract: On-policy distillation (OPD) has become a key paradigm in LLM post-training, yet its training dynamics remain poorly understood. We present a systemat
arXiv:2607.13792v1 Announce Type: new Abstract: Most daily activities are inherently procedural. However, existing evaluations for egocentric video understanding seldom address procedural understandin
arXiv:2607.13072v1 Announce Type: cross Abstract: Zero-shot object-goal navigation aims to enable an intelligent agent to explore and navigate to objects of unknown categories in an unfamiliar environ
arXiv:2607.13245v1 Announce Type: new Abstract: While 3D Scene Graphs (3DSGs) provide crucial structured representations for embodied agents, conventional Ahead-of-Time, build-everything-then-filter p
arXiv:2510.11686v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) promises to expand the capabilities of language models, but it is unclear if current RL techniques promote the dis
arXiv:2607.13075v1 Announce Type: cross Abstract: Context can change whether a request is harmful without changing its topic or surface form. We ask whether residual-stream probes distinguish harmful
arXiv:2607.13292v1 Announce Type: new Abstract: Autoformalization translates informal natural language into formal, machine-verifiable languages. While most work focuses on individual statements, real
arXiv:2607.12200v1 Announce Type: new Abstract: As frontier language models advance, policymakers and model developers need methods for assessing whether model access materially increases a non-expert
Across 101 enterprises, agent orchestration is consolidating onto model-provider platforms — Anthropic’s Claude leads by a wide margin — chosen for the gravity of the underlying model and judged on re
arXiv:2607.12278v1 Announce Type: new Abstract: Recent vision-language models (VLMs) for computational pathology report striking zero-shot performance on whole-slide image (WSI) visual question answer
arXiv:2607.12058v1 Announce Type: cross Abstract: Given a vulnerability-fixing commit, trigger localization asks which specific statement turns the vulnerable program state into a concrete unsafe oper
arXiv:2607.12789v1 Announce Type: cross Abstract: The O(N^2) complexity of attention over N tokens remains a computational bottleneck in transformer models. Vector-Quantized (VQ) attention reduces thi
arXiv:2607.11945v1 Announce Type: new Abstract: Capable language models hold what a character believes apart from what is true: told 'Anna believes the cup is blue; in reality it is red,' they answer
Below Upstream Status sections are from https://github.com/PrismML-Eng/Bonsai-demo Upstream Status for Binary Q1_0 is supported out of the box in upstream llama.cpp across many backends: CPU (generic,
arXiv:2607.11891v1 Announce Type: cross Abstract: The deployment of large language models (LLMs) in specialized domains like medical diagnostics and financial advisory necessitates evaluating capabili
arXiv:2607.12220v1 Announce Type: new Abstract: Synthesizing deployable robot behavior trees (BTs) from natural language (NL) requires grounding to ensure every generated BT references only skills a r
arXiv:2607.12404v1 Announce Type: new Abstract: Learning representations that separate content and style is crucial for controllable generation and compositional generalization. However, diffusion and
arXiv:2511.09483v3 Announce Type: replace Abstract: While multimodal large language models can describe visual content, their ability to generate executable procedures remains underexplored. CrochetBe
Efficiency defined as score over active parameters. Removed all the models that were not on the pareto frontier. Yes I'm aware that artificialanalysis.ai aggregate benchmark isn't perfect, but I have
arXiv:2607.11638v2 Announce Type: replace Abstract: City-scale outdoor navigation is currently hindered by the heavy reliance on dense maps or costly navigation supervision. In this work, we introduce