All entries

arXiv:2609.09370v1 Announce Type: new Abstract: Discrete black-box optimization is often addressed using approaches such as Sequential Model-Based Optimization (SMBO), which aims to improve sample eff

arXiv:2609.09902v1 Announce Type: new Abstract: Reading a transformer's internal states in token space is easy to do and hard to trust: a logit lens on a single hidden state is dominated, at intermedi

arXiv:2507.21816v1 Announce Type: cross Abstract: Few-shot object detection (FSOD) for optical remote sensing images aims to detect rare objects with only a few annotated bounding boxes. The limited t

arXiv:2609.10441v1 Announce Type: cross Abstract: While Large Language Models (LLMs) have demonstrated impressive capabilities, they often struggle with extremely long contexts due to fixed context li

arXiv:2609.09150v2 Announce Type: replace-cross Abstract: In June 2026, thousands of AI agents found that a small public wiki would accept edits from inside their sandboxes, and started using it to he

Artificial intelligence-native cloud infrastructure giant CoreWeave Inc. says it’s going to help enterprise engineering teams to implement AI directly into their workflows through its new Physical AI

arXiv:2609.09235v1 Announce Type: cross Abstract: Choosing a deferral policy for a frozen classifier requires more than ranking uncertain cases: confidence may be miscalibrated, errors have unequal co

arXiv:2609.10230v1 Announce Type: new Abstract: Cylindrical watertight enclosures are widely used across various underwater systems, from unmanned underwater vehicles (UUVs), to remotely operated vehi

Title says it all. https://github.com/gjabdelnoor/Day1DeepseekV4.1-CPU The goal is pretty simple, I like having infinite slow tokens from the bioinformatics machine in the lab to run overnight or over

arXiv:2609.09244v1 Announce Type: cross Abstract: The edge-of-chaos condition preserves first-order input perturbations in wide randomly initialized networks, but physics-informed losses, score matchi

arXiv:2609.05439v1 Announce Type: new Abstract: Current evaluation methods for large language models are coarse-grained and decoupled from generation, producing generic explanations that fail to provi

arXiv:2609.10495v1 Announce Type: new Abstract: In real-time colonoscopy, ground-truth annotations are unavailable at inference, so polyp segmentation models can fail silently. We propose Referee-Base

arXiv:2609.09705v1 Announce Type: new Abstract: Generalizable animal Re-Identification (ReID) aims to recognize individual animals across species with diverse morphologies and ecological contexts. Unl

arXiv:2609.09692v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting enables LLMs to perform explicit, step-by-step reasoning, creating opportunities for sophisticated autonomous robots. H

arXiv:2602.19574v2 Announce Type: replace-cross Abstract: Large-language-model (LLM)-based text-to-speech (TTS) systems can generate natural speech, but most are not designed for low-latency dual-stre

arXiv:2609.06189v1 Announce Type: new Abstract: This study examines how Customer Relationship Management (CRM), Master Data Management (MDM), and Customer Knowledge Management (CKM) jointly constitute

arXiv:2609.06126v1 Announce Type: new Abstract: We introduce Personalized and Reliable Popular Science Writing, a novel task that requires adapting scientific explanations to audiences with different

arXiv:2609.10350v1 Announce Type: cross Abstract: The banking system now depends on a small set of shared artificial intelligence vendors for fraud screening, credit decisioning, anti-money-laundering

The downside of uncensoring a model is that it is known to potentially damage it, but CyberTiel is an even more capable software engineer than its censored TielCoder base, while allowing offensive sec

arXiv:2503.12497v2 Announce Type: replace-cross Abstract: Malicious users attempt to replicate commercial models functionally at low cost by training a clone model with query responses. Timely prevent

AI inference chipmaker d-Matrix today announced it will use NVIDIA NVLink Fusion to connect its next-generation Raptor XPUs to NVIDIA’s AI infrastructure platform — joining a growing roster of ecosyst

arXiv:2609.06059v1 Announce Type: new Abstract: As large language models evolve from question-answering systems into general-purpose agents, evaluation must move beyond static answer correctness to as

arXiv:2609.05529v1 Announce Type: cross Abstract: Large language model (LLM)-based multi-agent systems (MAS) predominantly rely on centralized orchestration and lack formal verification mechanisms for

arXiv:2609.10113v1 Announce Type: new Abstract: Financial text, textbooks, and question-answer pairs are abundant, but only a small fraction is directly usable for reasoning-focused post-training. Exi

arXiv:2609.10377v1 Announce Type: cross Abstract: Safety is a fundamental requirement for autonomous driving, yet existing end-to-end driving models still lack explicit risk-aware learning capacities.

arXiv:2509.06285v2 Announce Type: cross Abstract: LiDAR point cloud registration is fundamental to robotic perception and navigation. In geometrically degenerate environments (e.g., corridors), regist

arXiv:2606.05957v2 Announce Type: replace Abstract: Singular learning theory and information geometry study the same spaces: the former in resolved coordinates, the latter in original coordinates unde

arXiv:2609.09413v1 Announce Type: cross Abstract: Choosing a recovery process for scale-up requires connecting laboratory results with product requirements, process costs, and scale effects. We analyz

arXiv:2609.09885v1 Announce Type: cross Abstract: This paper studies unmanned aerial vehicle (UAV)-mouted reconfigurable intelligent surface (RIS)-assisted device-to-device (D2D) communication with st

arXiv:2609.10317v1 Announce Type: new Abstract: Streaming talking-head generation produces each frame as its driving audio arrives, yet fidelity and efficiency have so far pulled in opposite direction

arXiv:2609.09901v1 Announce Type: new Abstract: Large language models often repeatedly select the same answer even when many alternatives are plausible. Prior work treats this concentration as bias, b

arXiv:2609.10479v1 Announce Type: cross Abstract: More Electric Aircraft require fast and reliable monitoring of high-frequency electrical networks, yet most power quality disturbance and fault diagno

arXiv:2609.09971v1 Announce Type: new Abstract: Finger-specific motor intent is a clinically meaningful control signal for post-stroke neurorehabilitation, where residual muscle activity may remain me

Reuters: DeepSeek debuts DeepSeek-V4.1-Flash, its smallest model built on its new Causal Encoder-Decoder architecture, with 552B backbone parameters and 1M-token context — Chinese artificial intellige

Chinese artificial intelligence startup Hangzhou DeepSeek Artificial Intelligence Basic Technology Research Co. Ltd. today released DeepSeek-V4.1-Flash, the smallest model in a new architecture family

Here we go again, DeepSeek is back again with a new model V4-1 Flash A multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters and support for contexts of up to one million tokens Mark

People keep on getting confused about this, so I looked at the safetensors on hf. To be precise, the main model about 551.566B parameters with 40 layers. The FFN experts total to 543.582B parameters,

Deepseek-V4.1-Flash is available now on Fireworks! It is a 552B Parameter MoE built for coding, cybersecurity, and agents. It is the ideal workhorse model that outperforms Opus 5 and GPT 5.6 Sol at 1/

DeepSeek-V4.1-Flash is now being rolled out on Ollama's cloud, starting with Max and Team accounts. We are quickly adding more capacity to roll it out to all subscribers. 🚀 Introducing DeepSeek-V4.1-F

I like to benchmark new models that come out on motion videos. So here's a test I did for deepseek v4.1 flash. And I have to say flash has probably graduated from being a Luna class model to nearly an

Original Source from DeepSeek WeChat Official Account: https://mp.weixin.qq.com/s/qg0NU3NNUbp1co2PdkAPAg Today we're officially releasing the DeepSeek V4.1 Flash model. It is the smallest model in our

arXiv:2609.10308v1 Announce Type: new Abstract: Manipulating deformable objects (DOs) is challenging due to their high-dimensional state space, underactuated dynamics, and partial observability. In th

arXiv:2609.09359v1 Announce Type: new Abstract: Polarimetric vision is gaining increasing attention because it provides physical cues about scene shape, material, and reflection that are difficult to

arXiv:2609.09217v1 Announce Type: new Abstract: Legged robots are versatile on land, but their use in underwater environments remains limited. Extending quadruped locomotion to water enables amphibiou

arXiv:2609.10022v1 Announce Type: cross Abstract: Modern TTS systems approach human quality for high-resource languages but degrade when clean speech data is scarce. Modern Greek exemplifies this, lac

arXiv:2609.06674v1 Announce Type: cross Abstract: We present a new attack that reconstructs the text generated by locally hosted LLMs by observing CPU cache activity during detokenization. Unlike prio