Knowledge catalogue
arXiv:2609.29618v1 Announce Type: cross Abstract: We report an exploratory, single-seed ablation of TALH (Adaptive Latent Hybrid), a decoder-only language model with parallel Multi-head Latent Attenti
arXiv:2609.29371v1 Announce Type: new Abstract: This paper presents BanglaTurn, a corpus for end-of-turn detection in Bangla conversational speech, and a model trained on it. The corpus holds 35,374 s
Want to RL-train a model on your own task without building the infra? Use our new cookbook with @hud_evals: → Define your task + grader in HUD → Sample + train the model on Fireworks Define the task o
arXiv:2609.27611v1 Announce Type: new Abstract: Foundation models hold promise for generalizable analysis of structural brain magnetic resonance imaging (MRI) across development, aging and disease. Ho
arXiv:2512.04125v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated several emergent behaviors with scale, including reasoning and fluency in long-form text generation.
arXiv:2609.27753v1 Announce Type: new Abstract: Vision-language-action (VLA) models have become a powerful paradigm for generalist robotic manipulation, yet they are often reactive: the policy maps th
arXiv:2609.27385v1 Announce Type: cross Abstract: Time-series foundation models (TSFMs) provide forecasts for operational decisions, but accuracy alone does not determine their value. Evaluating agent
arXiv:2609.27511v1 Announce Type: cross Abstract: We present NV-Reason-CT, a generative vision--language model for chest and abdominal CT combining native 3D visual encoding with radiologist-guided re
arXiv:2609.26118v1 Announce Type: new Abstract: Latent action models (LAMs) learn action-related representations from action-free videos via self-supervised future prediction, offering a scalable para
arXiv:2609.25518v1 Announce Type: new Abstract: Attributing language model outputs to their internal computations is an open problem in interpretability. Existing methods, which use causal interventio
arXiv:2606.18473v2 Announce Type: replace Abstract: Machine unlearning for large language models (LLMs) aims to remove specified knowledge while preserving the rest of the model's capabilities. Howeve
arXiv:2602.04577v3 Announce Type: replace Abstract: Large language models present challenges for principled uncertainty quantification, in part due to their complexity and the diversity of their outpu
arXiv:2609.24052v1 Announce Type: new Abstract: Crash datasets that carry an investigator narrative hold information the coded fields omit. Coding those narratives at scale has been blocked by three o
arXiv:2609.24126v1 Announce Type: cross Abstract: Black-box machine learning models increasingly deliver strong predictions, but extracting useful information from them, such as a set of important fea
Over the last few hours, some requests to the deepseek-v4.1-flash model on Ollama were charged at an incorrect rate, leading to higher usage consumption than expected for certain users. Sorry about th
arXiv:2510.01365v2 Announce Type: replace Abstract: The ability to model mechanics of soft materials under flowing conditions is key in designing and engineering processes and materials with targeted
arXiv:2609.22854v1 Announce Type: cross Abstract: Vision-language-action models often predict actions from only the current observation, which can leave tasks involving object occlusion or visually id
arXiv:2609.24559v1 Announce Type: new Abstract: We present t_0, a family of open-weights foundation models for forecasting with multivariate context. We release its first two members: exttt{t0-alpha}
arXiv:2609.21225v1 Announce Type: new Abstract: Parametric CAD reconstruction requires recovering both precise geometry and editable modeling operations from visual observations, making it challenging
arXiv:2609.21712v1 Announce Type: new Abstract: Generative world models offer controllable and repeatable closed-loop simulation for end-to-end and vision-language-action driving policies, but product
Thanks @vllm_project for the day-0 support! 🙌 Generate, edit, transparent output — one model, ready to serve. Details 👇 Qwen-Image-2.1 from @Alibaba_Qwen has day-0 support in vLLM-Omni. 🎉 Generate, ed
First time trying something like this. I asked chatgpt and it told me there are mcp server plugins for both ghidra and ida pro as well as RE-MCP which has support for both. I could run that on my low
arXiv:2609.19716v1 Announce Type: new Abstract: Pre-trained 3D vision models have substantially advanced point cloud analysis, yet adapting them to downstream tasks via full fine-tuning is computation
Hot topic livestream: Learn about Jev A buzzy new model Jev, by @typesafeai, reports up to 200x faster inference and 400x lower cost than comparable LLMs on classification tasks. It's aiming to solve
arXiv:2609.20504v1 Announce Type: cross Abstract: FarmerChat is Digital Green's AI-powered agricultural advisory assistant for smallholder farmers, who access it in their own language through text, vo
arXiv:2609.18167v1 Announce Type: cross Abstract: Adapting to changes in robot dynamics requires learning from new data without discarding experience that may still be useful. In continual model-based
arXiv:2609.18107v1 Announce Type: new Abstract: Graph anomaly detection aims to identify graph structures (e.g., nodes, edges, or subgraphs) that deviate significantly from expected patterns, which su
arXiv:2609.18511v1 Announce Type: cross Abstract: In autonomous driving, perception models often struggle to generalize to new environments due to domain shifts. While unsupervised model adaptation of
This is basically an Opus 4.5/4.6 level model that will work on anything with 8 Gb RAM Today, we’re announcing Ternary Bonsai 2 27B. Based on Qwen3.8 27B, Bonsai 2 27B is 9x smaller than its full-prec
arXiv:2403.17612v3 Announce Type: replace Abstract: Labeling corpora constitutes a bottleneck to create models for new tasks or domains. Large language models mitigate the issue with automatic corpus
arXiv:2609.16031v1 Announce Type: cross Abstract: Ultra-low-dose computed tomography (ULDCT) reduces radiation exposure but suffers from severe noise that degrades diagnostic image quality. Existing d
arXiv:2609.17187v1 Announce Type: new Abstract: Accurate wheel slip estimation is essential for autonomous lunar rover mobility and navigation. Machine Learning models trained on terrestrial data gene
arXiv:2609.16060v1 Announce Type: cross Abstract: Users often need ask questions and seek answers online. The Question - Answering (QA) forums such as Stack Overflow cannot always respond to the quest
My name is Chris Painter, and I'm the President of METR (Model Evaluation and Threat Research). I know we've made a lot of new friends on the internet the last couple of days, so I thought I'd take th
arXiv:2602.10480v4 Announce Type: replace Abstract: Large language models (LLMs) exhibit strong general-purpose reasoning capabilities, yet they frequently hallucinate when used as world models (WMs),
arXiv:2609.17251v1 Announce Type: new Abstract: We introduce a simple architectural modification to decoder-only transformers: a persistent recurrent state that observes hidden representations via cro
arXiv:2609.17419v1 Announce Type: new Abstract: Long-horizon LLM agents must maintain task state across extended sequences of observations, actions, tool calls, and intermediate beliefs. We study thes
arXiv:2609.15603v1 Announce Type: cross Abstract: Accurate PSMA PET/CT interpretation is central to prostate cancer management, yet existing PET/CT AI models typically address isolated tasks. We propo
arXiv:2609.14462v1 Announce Type: new Abstract: Interactive video world models must maintain broad scene context under camera motion while producing high-fidelity observations with low latency. Existi
arXiv:2609.14709v1 Announce Type: new Abstract: Immune therapies act across cell-intrinsic programs, tissue ecosystems, and patient-specific immune states, yet most predictors address these scales sep
arXiv:2609.14248v1 Announce Type: cross Abstract: Faithful citation attribution begins with identifying the intended source for a scientific claim. We study this source-identification capability throu
arXiv:2609.13869v1 Announce Type: cross Abstract: Automatic sentence function identification is important for many downstream natural language processing (NLP) applications such as dialogue systems, t
arXiv:2609.13270v1 Announce Type: cross Abstract: In distributed model predictive control for multi-drone collision avoidance, a fixed prediction horizon forces a compromise: a short horizon is inexpe
arXiv:2609.15354v1 Announce Type: cross Abstract: Accurate cell detection and classification are crucial for pathological analysis, directly affecting diagnostic accuracy and treatment planning. To ca
arXiv:2512.10159v3 Announce Type: replace-cross Abstract: LLMs have shown strong performance in data-rich domains such as programming, but their reliability in engineering tasks remains limited. Circu
arXiv:2501.13707v3 Announce Type: replace-cross Abstract: The event-based Vision-Language Model (VLM) recently has made good progress for practical vision tasks. However, most of these works just util
arXiv:2407.02395v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used for program synthesis, yet they often generate code that is functionally plausible but inse
arXiv:2609.15870v1 Announce Type: new Abstract: Scaling generalist policy models with heterogeneous data is limited by the lack of unified, low-noise action supervision. Human egocentric videos are ab
arXiv:2602.21223v2 Announce Type: replace Abstract: It is not only what we ask large language models (LLMs) to do that matters, but also how we ask them. Phrases like ``This is urgent'' or ``As your s
【AIの難問は、生命の難問へ：英国王立協会が紐解く「世界モデル」と知能の未来】 近年のAIの急速な発展により、AGI、すなわち人間並みの知能はすでに実現したという意見も聞かれるようになりました。果たしてそうなのでしょうか。 鍵となるのが「世界モデル（World Model）」の概念です。 世界モデルとは、生き物やAIが外の世界を内部に写し取り、次に何が起きるかを予測して行動するための土台となるもの
Excited to continue our partnership with the @alibaba_cloud team on this one, bringing the latest version of Qwen's flaship model to the Fireworks community. Start building with Qwen3p8 today: https:/
arXiv:2609.11028v1 Announce Type: cross Abstract: LM-agent benchmarks increasingly function as interactive evaluation infrastructure. Agents observe state, call tools, modify workspaces, submit artifa
I have a full M5 Pro Macbook Pro with 48GB of RAM, I'm just getting into this local space. Like many of you, the costs of using frontier/cloud models is getting kinda silly. I don't have any insane ne
arXiv:2609.11061v1 Announce Type: new Abstract: Tree-structured rollouts give critic-free reinforcement learning with verifiable rewards (RLVR) step-level credit: fork a chain at an intermediate point
In my opinion the perfect model(s) will be around 20B-32B and A2B-A4B. This is the sweet spot on which companies should focus on. Qwen 3.8, Gemma E2B/E4B and Ling 3.0 proved it. They are still imperfe
🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient. 🔹 Introducing the smallest model in our new architecture family, with native visual understanding. 🔹 Designed for greater capability
Introducing Gen-1 Slides: an open model that matches Claude Opus 5 on slide generation, at ~1/17 of its input-token price. @genspark_ai post-trained it from a @MiniMax_AI M3 base with Fireworks Lab us
arXiv:2609.10055v1 Announce Type: cross Abstract: Biomedical ontology normalization maps free-text expressions to standardized concepts, enabling consistent integration and analysis of biomedical data
arXiv:2603.17523v2 Announce Type: replace Abstract: Neural operators (NOs) are powerful deep learning frameworks designed to learn solution operators of partial differential equations. This study eval
arXiv:2609.05575v1 Announce Type: cross Abstract: Understanding how concepts are encoded in the internal representations of machine learning models is a central problem in mechanistic interpretability