Self-Evolving Code-with-Image Reasoning
arXiv:2608.11292v1 Announce Type: new Abstract: Multimodal models increasingly reach for tools when solving visual tasks (crop, zoom, rotate, brighten), a paradigm known as thinking-with-images. The c
Knowledge catalogue
arXiv:2608.11292v1 Announce Type: new Abstract: Multimodal models increasingly reach for tools when solving visual tasks (crop, zoom, rotate, brighten), a paradigm known as thinking-with-images. The c
arXiv:2608.11350v1 Announce Type: new Abstract: Embodied agents are increasingly built as systems around foundation models, where performance depends not only on model weights but also on the skills,
arXiv:2606.09498v2 Announce Type: replace Abstract: The performance of LLM-based agents is jointly shaped by their base models and the harnesses that mediate their interaction with the environment. Be
arXiv:2608.11657v1 Announce Type: cross Abstract: We introduce Semantic Lenia, an artificial life framework that transforms Large Language Model (LLM) inference from a static optimization problem into
Stumbled across this new vision model, SenseNova-Vision. It's a 7B MoT model, Apache 2.0 license, which is cool. The main idea is it treats pretty much all computer vision stuff as just one generation
arXiv:2608.12026v1 Announce Type: new Abstract: Post-training quantization pipelines routinely leave the softmax output layer in high precision. Yet in small LLMs with modern vocabularies, the head ho
SpaceXAI today released Grok 4.6, a large language model that it says can outperform Anthropic PBC’s Claude Fable 5 in some areas. SpaceXAI was known as xAI until last month. The Elon Musk-founded art
arXiv:2509.13450v3 Announce Type: replace Abstract: We introduce SteeringSafety, a benchmark for evaluating representation steering methods across nine safety perspectives spanning 18 datasets. While
arXiv:2608.11671v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models can follow instructions and manipulate objects, but their performance often collapses out of distribution (OOD), whe
arXiv:2608.11938v1 Announce Type: new Abstract: Sparse voxel reconstruction offers an efficient representation for high-fidelity 3D modeling, yet its geometry is commonly optimized from local photomet
arXiv:2608.11452v1 Announce Type: cross Abstract: Text-to-image (T2I) models are increasingly asked to illustrate literary and cultural content, yet we cannot measure how well an image renders the mea
arXiv:2608.11474v1 Announce Type: new Abstract: Object Hallucination in large vision-language models (LVLMs), where models generate non-factual content about input images, remains a critical barrier t
arXiv:2608.11469v1 Announce Type: cross Abstract: AI agents are rapidly improving in cybersecurity capabilities when the source code is available for analysis, yet much of the software most consequent
arXiv:2607.11175v2 Announce Type: replace Abstract: The growing ability of large language models and vision-language models to jointly interpret and reason over images and text is reshaping medical im
According to a Twitter post by OpenAI on August 13, 2026, the top 10% of enterprises adopt AI plugins twice as frequently and leverage skills—such as model‐based knowledge and reasoning—six times more
arXiv:2608.11694v1 Announce Type: cross Abstract: A benchmark score comes from a single phrasing of each problem. That single phrasing is treated as if it stood for the whole space of ways the same pr
This week we launched the world's most accurate document extraction agent over real-world documents. Introducing LlamaExtract Agentic Plus 💫 . It is a complete document extraction model+harness engine
arXiv:2608.11375v1 Announce Type: new Abstract: In this paper, we test different methods for multivariate detection of outliers in the data of transmitted heat energy in the selected substation of loc
arXiv:2608.11238v1 Announce Type: new Abstract: Retrieval-augmented generation improves the factuality of large language models by grounding responses in retrieved evidence, yet existing evaluation fr
arXiv:2608.11236v1 Announce Type: cross Abstract: Roleplay evaluation should do more than assign a single score: it should reveal which role requirements were tested, which failed, and which dialogue
arXiv:2608.11415v1 Announce Type: cross Abstract: Large language models are being proposed as agents in scientific workflows, in domains where no downstream verifier exists. Such deployment assumes th
I've been googling 'tar extract gz' for about ten years. and I finally did something about it. It started out as a research project and I ended up with a Fine-tuned Qwen2.5-Coder-1.5B on 125k natural-
arXiv:2608.11223v1 Announce Type: cross Abstract: Entry-only automatic fare collection systems record boardings but not alightings, preventing direct construction of origin-destination (OD) matrices.
Try Grok 4.6 Grok 4.6 wins again. 👑 Grok 4.6 takes the #1 spot on GPQA Diamond with a score of 94.9%, beating GPT-5.6, Gemini 3.1 Pro, Claude Opus 5, and every other model tested by Artificial Analysi
arXiv:2608.12282v1 Announce Type: new Abstract: Agents deployed in enterprise settings must reason across structured APIs and document collections, yet existing benchmarks evaluate these capabilities
arXiv:2608.11435v1 Announce Type: new Abstract: Forward and inverse modeling of parametric dynamical systems requires surrogate models that are not only accurate for state prediction, but also informa
arXiv:2608.12246v1 Announce Type: cross Abstract: Evaluating security vulnerability detection tools requires benchmark datasets with vulnerability-inducing commits (VICs) - the commits that first intr
arXiv:2606.19985v2 Announce Type: replace Abstract: Occlusion-robust scene recovery remains a major challenge in computational imaging, particularly where dense vegetation severely limits visibility.
arXiv:2608.11883v1 Announce Type: new Abstract: Multimodal satellite imagery provides complementary information for Earth Observation, but accurately combining heterogeneous sensors remains challengin
arXiv:2602.14419v2 Announce Type: cross Abstract: This paper reformulates Transformer/Attention mechanisms in Large Language Models (LLMs) through measure theory and frequency analysis, theoretically
We tested out Anthropic’s J-Lens probe at two open models: Kimi K3 and Qwen 3.5-9B. By looking at their internal states, we found that the models are setting up the right vocabulary before a single to
arXiv:2608.11342v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) is a standard approach for adapting LLMs to a target distribution, but in settings such as personalization, where each au
We’re launching DeepSeek-V4-Pro today! 🚀 🔷 Major Agent upgrades with strong production gains! 🔷 Flexible reasoning effort for V4-Pro & V4-Flash: low for simple tasks, high for daily Agent workflows, m
We’re working with an initial group of customers to understand where this speed makes the biggest difference, and how those learnings can inform our products over time. If your business requires front
arXiv:2608.11560v1 Announce Type: new Abstract: Personalizing marketing messages with contextual multi-armed bandits (CMABs) drives real business value, yet the objective that ultimately matters - a d
arXiv:2608.11403v1 Announce Type: new Abstract: Self-consistency (SC) via majority vote is a widely used way to spend inference-time compute: sample N chains of thought, return the plurality answer. O
arXiv:2608.11715v1 Announce Type: cross Abstract: The reliability of Large Language Models (LLMs) for API calling degrades in multilingual settings. A common failure occurs when a model selects the co
Within Devin, Gemini 3.7 Flash performs particularly well on tightly scoped refactors, where it delivers minimal diffs that match repo conventions. Gemini 3.7 Flash is available at a 50% discount for
Generative artificial intelligence startup Writer Inc. today announced the release of its next-generation flagship model, Palmyra X6, designed to deliver frontier-level performance for marketing and r
arXiv:2608.11676v1 Announce Type: new Abstract: Heterogeneous multi-agent LLM systems, where agents are powered by different model families, can outperform homogeneous configurations by reducing redun
You don't stand up an agent. You upload a folder. Claude Code is a harness for your laptop. Managed Deep Agents is a harness for production. Want Slack? Add a file. Want a daily run? Add a file. Want
18 two-word AI prompts I'm kind of obsessed with: 1) now what - great for when you've wrapped up a project or big push and you still have energy and want AI to give you more 2) plz fix - usually accom
arXiv:2608.10978v1 Announce Type: new Abstract: Optical music recognition (OMR) transcribes music scores into digital formats. While the field has advanced significantly on monophonic and piano-form s
arXiv:2608.10588v1 Announce Type: cross Abstract: Purpose: Fine-grained handshape recognition supports computational sign-language transcription, recognition, and translation, but broad, phonetically
arXiv:2608.10418v1 Announce Type: cross Abstract: Recent work has shown that, for smooth convex optimization, plain gradient descent can be accelerated from its textbook convergence rate of O(T^{-1})
arXiv:2608.10235v1 Announce Type: new Abstract: Hamiltonian Neural Networks (HNNs) parameterize conservative dynamics through a learned scalar Hamiltonian, providing an architectural prior that is abs
arXiv:2608.11173v1 Announce Type: cross Abstract: The attention mechanism forms the foundation of many modern AI models such as the Transformer. In one subclass of problems where attention is used, in
arXiv:2406.12659v3 Announce Type: replace-cross Abstract: We propose a scalable variational Bayes method for statistical inference for a single or pre-specified low-dimensional subset of the coordinat
arXiv:2608.10430v1 Announce Type: cross Abstract: Large Language Models (LLMs) deployed as AI agents frequently exhibit user specification-grounding failures, executing hallucinated, undesired actions
Marketing intelligence company Ahrefs Pte. Ltd. today launched Letaido, an agent-powered marketing workspace built to take over the recurring research, reporting and monitoring work that fills up a ma
arXiv:2608.09959v1 Announce Type: cross Abstract: AI weather models are in the process of revolutionising weather forecasting. While these models have been shown to achieve superior performance to phy
arXiv:2608.09948v1 Announce Type: cross Abstract: No single AI weather model excels at all variables, pressure levels, and lead times. Rather than building yet another architecture, we reframe the for
arXiv:2508.03611v3 Announce Type: replace-cross Abstract: This paper presents Astrolabe, a randomized prediction-guided scheduler for one-shot request dispatch in multi-instance large language model (
arXiv:2608.11138v1 Announce Type: cross Abstract: We propose that a model's uncertainty about a token is reflected not only in the breadth of its output distribution but also in whether a confident pr
Enterprise content is no longer just something people consume. As organizations increasingly rely on AI to extract and act on information from documents, images, audio, and video, Azure Content Unders
mtmd: support pocket-tts (#26871) adapt the api text model ok working impl, need verify and clean up mtmd: build the pocket-tts transposed convolutions as GEMM + col2im ggml_conv_transpose_1d has no g
imatrix.cpp: Move finite check and only check touched experts (#26861) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS In
chat : tighten bare function parsing for Qwen models (#26793) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)
common: Add CLI > ENV > models-presets > INI precedence CLI flags have the highest precedence ENV vars have the second-highest precedence System and User configs have the lowest precedence Linux/BSD/M
arXiv:2606.08348v2 Announce Type: replace Abstract: LLM agents increasingly rely on prompts, tools, memory, SOPs, skills, and harness feedback, yet current self-evolution pipelines often update these