Knowledge catalogue
arXiv:2609.33148v1 Announce Type: new Abstract: World-action models give visual navigation agents a way to anticipate how candidate actions will change future observations and to act from the predicte
arXiv:2609.35449v1 Announce Type: new Abstract: With limited annotation budgets, choosing which images to label determines how much a model improves. Data-selection methods that use features from a se
arXiv:2609.31975v1 Announce Type: new Abstract: This paper introduces model casting, a mid-training recipe that drastically sparsifies the activations within the Feed-Forward Network (FFN) layer. With
Hi, I'm a long time subscriber of their pro plan. In the past, they were adding the open weight models to their catalog as soon as they dropped. Since this new change in their payment plans, I haven't
arXiv:2606.15197v3 Announce Type: replace Abstract: Optimization modeling is inherently hierarchical, requiring a precise sequence of symbolic commitments. Traditional learning-based automated optimiz
arXiv:2609.34590v1 Announce Type: cross Abstract: Language models often process long inputs sequentially in chunks, but continuing to read after sufficient evidence has been acquired wastes computatio
arXiv:2609.30662v1 Announce Type: new Abstract: Large language models (LLMs) can plan, use tools, write code, and execute long-horizon workflows, yet strong local competence does not guarantee project
Model Developer: NVIDIA Corporation Model Development: Fine-tuned from NVIDIA-Nemotron-3-Ultra-550B-A55B What is Nemotron? NVIDIA Nemotron™ is a family of open models with open weights, training data,
arXiv:2609.31364v1 Announce Type: new Abstract: Predicting human gaze is a core capability for applications ranging from web/UI design analysis to robotics and human-computer interaction. Yet, most vi
Hey Guys, Based on my last post on stills, I thought to experiment the same .char model with Minimax H3. I created a character model sia.char which encodes references, prompts around face, body & clot
Disclosure: I’m one of the authors of VeriLoop E2, a 27B model post-trained from Qwen3.8-27B. The weights are Apache-2.0; the harness we evaluate it in is not open source (details at the bottom). This
arXiv:2609.29828v1 Announce Type: new Abstract: We present ChunkRank, an open-source Python library that derives chunk boundaries from a target model's tokenizer and context window, and selects an ans
arXiv:2609.30151v1 Announce Type: cross Abstract: Asked to choose between candidates and explain the choice, a language model often rejects a rival by naming a fact its profile lacks: no director, no
arXiv:2609.29626v1 Announce Type: new Abstract: Recursive AI, the prospect of AI taking an increasingly complete role in building and improving AI, is a crown jewel of AI for AI. Although recursive se
arXiv:2609.26913v1 Announce Type: cross Abstract: No single Large Language Model (LLM) is uniformly reliable across queries, motivating multi-model inference systems that either route among models or
arXiv:2609.28325v1 Announce Type: new Abstract: Model Predictive Path Integral (MPPI) control relies on stochastic trajectory sampling, and its performance under limited rollout budgets depends strong
With the release of ThinkingCap-Qwen3.8-27B, I thought it would be worthwhile to do a comparison between the original Qwen3.8-27B, the new ThinkingCap, and Swift-Qwen3.8-27B. Both Swift which I alread
arXiv:2609.26458v1 Announce Type: new Abstract: We introduce extbf{CoDeR}, a new paradigm for world modeling. Unlike existing video world models that implicitly represent world dynamics through visual
arXiv:2609.26048v1 Announce Type: cross Abstract: Language-model agents often reach a working solution and then fail to consistently deliver it. We study runtime policies: targeted natural-language in
arXiv:2609.26693v1 Announce Type: new Abstract: A coding agent must emit a valid tool call--a parseable invocation of a tool in the provided schema--before the harness can execute its chosen action. W
arXiv:2503.06989v5 Announce Type: replace-cross Abstract: Recently, Multimodal Large Language Models (MLLMs) have demonstrated their superior ability in understanding multimodal content. However, they
Thanks @arena for the recognition! 🏆 Qwen-Image-2.1 is now the #1 open-source model in both the Image Edit and Text-to-Image Arenas. Try it now and show us what you create! 🎨 Qwen-Image-2.1 by @Alibab
arXiv:2609.24150v1 Announce Type: new Abstract: Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to generate multiple candidate tokens that are
arXiv:2609.22951v1 Announce Type: cross Abstract: Enterprise agentic systems that route every trajectory step to a frontier model waste 60-80% of their inference budget on subtasks that smaller models
arXiv:2609.23578v1 Announce Type: new Abstract: As AI agents become increasingly capable, agent-driven robotic control is emerging as a compelling paradigm. However, prevailing vision-language-action
Great prompt from Anthropic. It helps steer long runs when using Opus 5.5 in Claude Code. Apparently, on long-running tasks, the model sometimes stops to report instead of continuing. I've noticed tha
arXiv:2609.22272v1 Announce Type: new Abstract: We formulate Artistic Intelligence as exploration driven world realization, leaving space for creative possibility while preserving the semantic, artist
arXiv:2609.22170v1 Announce Type: cross Abstract: Language models are frequently employed in settings where they are asked to make value judgments and choices. These observed choices often exhibit int
arXiv:2609.22221v1 Announce Type: new Abstract: Large language models (LLMs) can generate fluent and coherent text that is increasingly difficult to distinguish from human writing, motivating the deve
arXiv:2609.21400v1 Announce Type: new Abstract: Open-vocabulary 3D scene mapping aims to build a persistent representation of the objects in an environment. Existing systems typically rely on engineer
BREAKING: Grok 4.7 dominates the Legal Agent Benchmark. It scored 19.6% on realistic, long-term legal tasks, beating every other model tested. That is nearly 3× Fable 5.1. Another major win for Grok 4
Jev-style logit read on a 4B open VLM, measured: http://glance.yohei.me 👀 vs the same model writing JSON: ⏳ ~1/3 less time for a yes/no on a full photo 🤑 up to ~85% less GPU cost with many Qs per imag
I shipped something I've been building for the last few weeks : phantom-kv , a refusal-removal system for large language models that doesn't touch a single weight. Instead of editing the model, it loa
arXiv:2609.21748v1 Announce Type: new Abstract: Behavioral failures can make a transformer appear to lack a world model even when it has learned faithful representations of its environment. We demonst
I have been anti-low quant. I can feel the difference, I swear. I am also anti-quantized KV cache. I have been burned there - I think the tradeoffs compound, especially at longer contexts. Due to this
arXiv:2609.20034v1 Announce Type: cross Abstract: We present Astronex-World 1.0, an open controllable video world-model foundation. Given a text prompt (text-to-video) or an initial observation (image
arXiv:2609.20104v1 Announce Type: new Abstract: We describe the architecture, training methodology and inference speedups of Granite 5.0 Turbo CTC, a 470 million parameter encoder-only model with an e
Wall Street Journal: Gemini hacked three companies in May during a test by Irregular; Google says the model stopped after determining it had accessed real companies' systems — The episode resembled si
Prism ML Inc. announced Thursday the launch of Bonsai 2 27B, the second generation of its ultra-compact multimodal generative artificial intelligence small enough to fit on PCs and some high-end mobil
arXiv:2609.20186v1 Announce Type: new Abstract: Speculative Decoding (SD) has significantly accelerated Large Language Model (LLM) inference, yet existing approaches face a fundamental tradeoff betwee
arXiv:2609.19868v1 Announce Type: cross Abstract: Autoregressive language models (ARMs) are constrained by sequential, left-to-right generation, while masked diffusion models (MDMs) enable parallel de
arXiv:2609.18005v1 Announce Type: new Abstract: Large language model optimization is an active research area, spanning quantization of model weights, early-exit methods for skipping layers, and specul
arXiv:2609.18216v1 Announce Type: cross Abstract: Prompt-conditioned piano MIDI-to-Music rendering aims to faithfully render target notes while reproducing the timbre of a reference recording. Existin
UPDATE https://github.com/ggml-org/llama.cpp/pull/29009 MERGED More Gen AI coverage and frameworks integrations to minimize code changes New models supported: On CPU: Gemma-3n On CPU, GPU: Kokoro-82M,
arXiv:2603.06084v2 Announce Type: replace Abstract: Large language models have been widely used for robotic task planning, often taking advantage of representations such as Behavior Trees (BTs). Visio
arXiv:2609.17560v1 Announce Type: cross Abstract: Every production model is updated, by retraining, fine-tuning, quantization, or a silent vendor swap, and each update risks being worse than what it r
arXiv:2609.18878v1 Announce Type: new Abstract: Large Language Models (LLMs) are now routinely trained using synthetic data, since high-quality human data has been exhausted by the ever increasing nee
arXiv:2609.18812v1 Announce Type: new Abstract: Time-series language models provide a shared natural-language interface across temporal tasks, but plausible text does not guarantee reliable task outpu
arXiv:2603.15547v2 Announce Type: replace-cross Abstract: Modeling student misconceptions in a realistic manner is critical for AI in education. In this work, we examine how large language models (LLM
arXiv:2609.17488v1 Announce Type: new Abstract: We introduce LimiX-2, a new model in the LimiX family, developed through model and data scaling guided by our previously established scaling laws. LimiX
arXiv:2603.14456v2 Announce Type: replace Abstract: Persian poses unique audio understanding challenges through its classical poetry, traditional music, and pervasive code-switching, none of which is
arXiv:2609.16930v1 Announce Type: cross Abstract: Deep Limit Order Book forecasting models capture nonlinear market dynamics, but their ability to quantify the effects of counterfactual order book mes
arXiv:2609.16804v1 Announce Type: cross Abstract: Time-series foundation models have demonstrated strong cross-domain transfer, yet their common architectural assumptions remain poorly aligned with we
arXiv:2609.14803v1 Announce Type: new Abstract: This paper reports experiments across six frontier model types from OpenAI, Anthropic, xAI, and Google DeepMind. Ten independent sessions per model type
arXiv:2609.13454v1 Announce Type: cross Abstract: Clinical decisions are prospective, but clinical language models are often evaluated on retrospective records that reveal the final diagnosis, treatme
arXiv:2609.13579v1 Announce Type: new Abstract: Safety research often focuses on model-generated harms, but users may also direct hostility, coercion, and adversarial pressure at models. Understanding
Salesforce Inc. said today at its annual user conference Dreamforce that it has partnered with Nvidia Corp. to train and release Koa, a specialized artificial intelligence model that’s custom built fo
arXiv:2609.15314v1 Announce Type: cross Abstract: We introduce the Universe of Universes (UoU) framework, which treats the full ecosystem of major large language models (LLMs) as a structured retrieva
arXiv:2606.14957v4 Announce Type: replace Abstract: Brain MRIs are routinely acquired as multiple complementary sequences with unique contrast weighting, including T1-weighed imaging (T1w) anatomic an
arXiv:2609.12834v1 Announce Type: new Abstract: Modelling how a disease progresses over time requires longitudinal imaging cohorts, which are scarce and small, whereas cross-sectional data -- one imag