All entries

arXiv:2609.30222v1 Announce Type: cross Abstract: Existing point tracking models face a fundamental tradeoff: they can either track a sparse set of query points over long horizons, or track all points

arXiv:2609.29951v1 Announce Type: cross Abstract: State tracking requires composing a sequence of updates, but accuracy alone does not reveal what a model has learned. We study neural networks trained

I have a tool that uses Gemini Flash with the lowest thinking budget to do summarization work. It's very fast, 0.9-1.2s in most cases. But I have a user experience problem where people make the wrong

arXiv:2609.30134v1 Announce Type: new Abstract: Neural behavior cloning compresses demonstrations into large models, making individual actions difficult to trace and policy updates costly. Retrieval p

arXiv:2609.30026v1 Announce Type: new Abstract: Detecting which holds a climber uses, and when, underpins automated scoring, movement analysis, and assistive systems for sport climbing. Existing appro

arXiv:2609.28654v1 Announce Type: new Abstract: Object permanence and solidity are hallmarks of human cognitive priors. Recent studies show that video generation models, a paradigmatic class of curren

arXiv:2609.29405v1 Announce Type: cross Abstract: We adapt Reinforce Adjoint Matching (RAM), a reward-based post-training method, to generative speech enhancement (SE). Starting from a pretrained SE m

arXiv:2609.29060v1 Announce Type: cross Abstract: Transformers achieve remarkable performance by jointly learning broad families of tasks during pretraining and adapting to unseen tasks from only a sh

arXiv:2609.29633v1 Announce Type: cross Abstract: We present TTLab's submission to the AlexandriaX-2026 Subtask~3 on Arabic MT error span detection and classification. Our system frames the task as to

arXiv:2609.29733v1 Announce Type: new Abstract: Arabic-language stance detection remains challenging, and previous shared-task systems have largely relied on multitask learning and ensembles. While th

arXiv:2609.28506v1 Announce Type: new Abstract: TW3Cast is a time-series forecasting system that reaches position 3 of 130 entries on the GIFT-Eval benchmark by mean MASE rank, as of 2026-09-14. The t

arXiv:2609.28575v1 Announce Type: new Abstract: Long-conversation memory benchmarks increasingly test recall and prompted knowledge updates, and recent work studies evolving user beliefs and memory st

arXiv:2609.29445v1 Announce Type: new Abstract: We audit a multilingual affective generation benchmark eight instruction-tuned LLMs producing emoji summaries for 17,100 Bangla, English and Hindi sente

arXiv:2609.26758v2 Announce Type: replace Abstract: Typed decision models are built for settings where model outputs are consumed directly by software. Instead of generating free-form text, they retur

arXiv:2609.29419v1 Announce Type: new Abstract: Autonomous navigation in dynamic environments is hindered by two fundamental challenges: perception instability and uncertainty-optimization mismatch. T

arXiv:2609.28610v1 Announce Type: new Abstract: Benchmarking is an increasingly critical part of research in machine learning and the domains where it is applied, including healthcare. Yet, despite th

arXiv:2609.28838v1 Announce Type: cross Abstract: Online reinforcement learning fine-tuning of pretrained flow-matching vision-language-action (VLA) policies promises robots that keep learning after d

arXiv:2609.28578v1 Announce Type: new Abstract: The increasing adoption of electric vehicles (EVs) and rooftop photovoltaic (PV) systems is reshaping residential electricity demand and creating new ch

arXiv:2609.29697v1 Announce Type: cross Abstract: Feedback-based planning improves agent reliability by incorporating tool observations and corrective feedback. However, its protection may not be dist

arXiv:2609.30214v1 Announce Type: cross Abstract: We present Underwater C^{3}-JEPA (cross-view, control-conditioned, context-extended), an object-centric multi-view predictive world model for near-fie

At Google Cloud, we are committed to delivering the best managed experience backed by open source software. Today, we’re announcing the general availability of Memorystore for Valkey 9.1, which achiev

arXiv:2609.28725v1 Announce Type: cross Abstract: Machine learning-based Network Intrusion Detection Systems often report near-perfect performance on IoT benchmarks. However, whether these models lear

arXiv:2508.18192v2 Announce Type: replace Abstract: Large Language Models (LLMs) have reshaped our world with significant advancements in science, engineering, and society through applications ranging

arXiv:2609.29553v1 Announce Type: cross Abstract: Automatic stress recognition from facial video provides a non-contact approach for affective monitoring. However, most existing video-based methods di

arXiv:2609.28605v1 Announce Type: cross Abstract: The Factivity Inference Evaluation 2026 (FIE2026) classifies Chinese context-hypothesis pairs into nine ordered factivity intervals. Its evaluation me

arXiv:2609.29118v1 Announce Type: new Abstract: LiDAR place recognition is a key front end for loop closure and global relocalization, yet indoor retrieval remains difficult when attitude or sensor mo

arXiv:2609.28722v1 Announce Type: new Abstract: While Federated Learning (FL) has been widely adopted for protecting user privacy in machine learning, it remains vulnerable to various robustness chall

Add manifest-list storage so runner-specific manifests can coexist under one tag while preserving existing v1 tags as best-effort downgrade anchors. Show/list/copy/remove/pull/push now understand runn

Identity governance must accommodate changing relationships among people, institutions and technology. Vanderbilt University sees that complexity deepening as artificial intelligence agents enter inst

arXiv:2609.28792v1 Announce Type: new Abstract: Robust average-reward Markov decision processes provide a fundamental framework for long-term performance optimization under uncertainty, and can have o

We’ve released the complete VeriLoop E2 GGUF precision ladder, from the canonical BF16 reference down to a mixed-precision IQ1_M deployment tier. This post is specifically about the GGUF release and l

arXiv:2609.29650v1 Announce Type: new Abstract: Tabular-to-image encoding methods enable the application of models based on both convolutional neural networks and vision transformers to tabular data,

arXiv:2609.30005v1 Announce Type: new Abstract: Vietnamese speech research is constrained by resources that isolate automatic speech recognition from speaker, dialect, code-switching, and deepfake ana

arXiv:2609.28923v1 Announce Type: new Abstract: Few-step autoregressive (AR) video diffusion enables low-latency streaming generation, but existing post-training methods predominantly rely on Distribu

arXiv:2609.29555v1 Announce Type: new Abstract: Navigation World Models (NWMs) predict action-conditioned visual futures for planning. Two practical challenges are central to their design: selecting a

Hello! I am currently building my local AI server, I have the Huananzhi H12D-8D EPYC Motherboard with 8x16GB memory sticks at 2666 mhz (waiting for the other components at the moment) I currently have

arXiv:2609.30221v1 Announce Type: new Abstract: Video generation begins in text space by authoring a cinematic screenplay, then materializes into pixels. As contemporary video generators scale to 30 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

I run a personal always-on agent fleet — eight seats claiming work in parallel from a shared task board, routing across Anthropic, OpenAI, xAI, Google, and a local Ollama floor. This week the spend fo

arXiv:2601.19753v2 Announce Type: replace Abstract: Underwater 3D reconstruction and appearance restoration remain challenging due to the complex optical properties of water, such as wavelength-depend

We announced our RSI Lab earlier this year: https://sakana.ai/rsi-lab/ Over the last two years, we have systematically shipped the foundations for autonomous R&D: ▪ LLM²: AI automating research to inv

We had already requested comment from 14 sports figures who got paid to speak at/promote Life Surge (on account of allegations like the ones below). We've already exchanged messages with several of th

arXiv:2609.29396v1 Announce Type: new Abstract: This paper presents and evaluates a Deep Learning-based (DL-based) Signal Quality Assessment (SQA) model to distinguish between clean and noisy ambulato

arXiv:2609.29772v1 Announce Type: new Abstract: Radar nowcasting is essential for short-term warning and emergency response, yet conventional systems mainly return future radar fields and provide limi

arXiv:2507.00938v4 Announce Type: replace-cross Abstract: Foundation models now enable autonomous agents to interact with real-world websites, but existing benchmarks emphasize general-purpose browsin

We’re building Copilot as a new OS for work that spans every model, every form factor, and every task. Today, we’re announcing our biggest update to Copilot to date, bringing four things together: · A