Knowledge catalogue
Qwen3.8-Flash on @qwen_cloud: 0.15/1M input tokens, 0.47/1M output tokens, and just 0.016/1M on cache hits. ☁️ Come give it a try! 👇 Qwen3.8-Flash API is live on QwenCloud. 262K native context, extens
arXiv:2608.26053v1 Announce Type: cross Abstract: Reasoning in language allows foundation models to spend more test-time compute on hard problems, such as those requiring decomposition, constraint tra
arXiv:2608.25585v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models provide a versatile foundation for general robotic manipulation, yet they exhibit significant brittleness when confr
arXiv:2608.25366v1 Announce Type: new Abstract: In this paper, we propose RAEM, a robust autonomous exploration framework for quadruped robots operating in multi-floor environments. Most existing grou
arXiv:2608.25236v1 Announce Type: cross Abstract: Clinical decision-making often involves prioritizing ethical values, such as beneficence, non-maleficence, respecting a patient's autonomy, and justic
arXiv:2509.21054v2 Announce Type: replace-cross Abstract: Understanding persuasion is critical for the safety and reliability of multi-agent systems built on large language models (LLMs). This paper s
arXiv:2603.19523v2 Announce Type: replace Abstract: Fingerspelling is a critical component of British Sign Language (BSL), used to spell proper names, technical terms, and words that lack established
arXiv:2608.25655v1 Announce Type: new Abstract: Conversations with chat assistants increasingly span many topics in a single long-running thread, challenging memory systems. Existing long-context and
arXiv:2509.08897v2 Announce Type: replace-cross Abstract: With the rapid advancement of multimodal retrieval and its application in LLMs and multimodal LLMs, increasingly complex retrieval tasks have
arXiv:1807.04783v3 Announce Type: replace Abstract: Can advances in NLP help advance cognitive modeling? We examine the role of artificial neural networks, the current state of the art in many common
Serving automatic speech recognition (ASR) models at scale is costly when each request uses only a fraction of a GPU. Learn how NVIDIA CUDA Multi-Process Service (MPS) with NVIDIA Triton Inference Ser
arXiv:2510.09062v2 Announce Type: replace Abstract: Recent advances in long chain-of-thought (CoT) reasoning have largely prioritized answer accuracy and token efficiency, while overlooking aspects cr
arXiv:2608.25140v1 Announce Type: cross Abstract: Existing approaches to building line-level Arabic handwritten-text-recognition (HTR) training data either rely on fully manual annotation, which does
arXiv:2608.25542v1 Announce Type: cross Abstract: Large reasoning models often produce reasoning traces with verification, revision, and backtracking. When reflection merely re-checks established resu
arXiv:2608.25390v1 Announce Type: new Abstract: Refusal training protects AI models from jailbreaks by training models to decline unsafe queries, reducing the risk of misuse. Recent work finds that re
arXiv:2608.26101v1 Announce Type: new Abstract: Recent advances in video editing have been largely driven by large-scale instruction-based datasets. However, existing datasets still suffer from two cr
arXiv:2603.15857v2 Announce Type: replace-cross Abstract: Behavioral Foundation Models (BFMs) produce agents with the capability to adapt to any unknown reward or task. These methods, however, are onl
When Pythian rolled out Google Cloud’s Gemini Enterprise across our 500-person company in 27 countries, the goal was simple: use our own company as a proving ground to discover how enterprise AI actua
arXiv:2608.25487v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has emerged as a powerful architecture for Question Answering (QA) by integrating external information into Large L
arXiv:2608.25221v1 Announce Type: new Abstract: We study exact representations of MAX_N(x)=max{x_1,ldots,x_N} using two-hidden-layer ReLU neural networks. This problem has been studied in recent years
Hi, I'm pretty sure I'm not the only one in this scenario, I have the Max Plan but I'm downgrading it to Pro and will buy GPT Plus because it's too much usage for my use cases. So either I waste money
arXiv:2608.25535v1 Announce Type: new Abstract: Wireless Internet-of-Things (IoT) edge networks require decentralized learning (DecL) methods that can operate reliably under both heterogeneous local d
arXiv:2608.25467v1 Announce Type: new Abstract: Multimodal regression suffers from the mean-collapse pathology: under squared loss, an unconstrained regressor converges to the conditional mean, which
arXiv:2608.24973v1 Announce Type: new Abstract: With the rapid development of large-scale pre-trained language models based on Transformer architectures, their high computational and memory costs have
arXiv:2608.25133v1 Announce Type: new Abstract: The development of federated learning (FL) techniques has helped improve the privacy preservation of users' data and extended the applications of machin
arXiv:2608.25037v1 Announce Type: cross Abstract: Product linking, the entity-resolution task of mapping merchant product records to canonical catalog products, consolidates fragmented listings so dow
arXiv:2608.24977v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) enhances large language models by grounding outputs in external knowledge, improving factuality and reducing hall
Generated about half locally on my 5070ti. But also bought cloud GPU time to speed up overall generation. Vibecoded a rolling cutter to chop the song into chunks and then feed it in as reference audio
arXiv:2608.26043v1 Announce Type: new Abstract: Multi-norm adversarial defense aims to protect neural networks against perturbations defined by different norm constraints, but existing methods typical
arXiv:2608.25017v1 Announce Type: new Abstract: A latent world model trains its decoder on latents anchored to observations, then deploys it on the model's own free-running rollout, hundreds of steps
arXiv:2608.25160v1 Announce Type: cross Abstract: Waveform inversion seeks to estimate the wave speed of a heterogeneous, inaccessible medium, from time-resolved measurements of the waves at user cont
arXiv:2608.25102v1 Announce Type: new Abstract: The Robot Operating System 2 (ROS2) has become a widely adopted framework for the development of distributed robotic systems. However, its communication
arXiv:2608.25277v1 Announce Type: new Abstract: Multi-agent LLM systems coordinate through natural-language messages that consume 40--60% of their token budget. Replacing these with structured graphs
arXiv:2608.25367v1 Announce Type: new Abstract: Underwater unimodal object detection faces many challenges in sensor imaging, such as optical images limited by underwater noise and visible distance, a
Runable Inc., a platform that uses artificial intelligence to help businesses build, run and grow, announced Wednesday that it has raised 21 million in early-stage funding to scale its operations and
I hit my token limit three times a day on my max subscription - got sick of that and designed this MCP setup to shift some of the coding load to my local Qwen3.8-27B model. I've been iterating on it n
arXiv:2608.25435v1 Announce Type: new Abstract: Fine-grained segmentation of communication-tower components in UAV imagery is essential for automated inspection, yet task-specific models are hard to d
arXiv:2608.24893v1 Announce Type: cross Abstract: In competitive first-person shooter (FPS) games such as Counter-Strike 2 (CS2), account-integrity review often asks whether an account's recent behavi
arXiv:2608.25910v1 Announce Type: new Abstract: Machine Learning (ML) is increasingly used in virtual prototypes of embedded systems to model behaviors that are difficult to capture analytically. Howe
arXiv:2506.23492v2 Announce Type: replace-cross Abstract: Recent advances in deep learning have significantly improved predictive accuracy. However, modern neural networks remain systematically overco
arXiv:2608.25304v1 Announce Type: cross Abstract: Multinomial choice models allow flexible substitution patterns but become computationally demanding with many alternatives or observations. With a fix
arXiv:2608.25890v1 Announce Type: cross Abstract: Detailed multicellular growth simulations based on subcellular element models (SEMs) can capture complex tissue development, but their element-level i
arXiv:2608.25095v1 Announce Type: cross Abstract: The proliferation of distributed energy resources (DERs) in distribution grids enables the active coordination of these assets to reduce costs and ena
arXiv:2510.22775v2 Announce Type: replace Abstract: While language model agents have advanced software engineering, existing test-based supervision is limiting its scalability on real-world issues. Th
arXiv:2602.12065v2 Announce Type: replace Abstract: We present Scene2Demo, a self-evolving framework for offline embodied data generation. Given a single real-world RGB image and a user query, Scene2D
arXiv:2608.25973v1 Announce Type: cross Abstract: Understanding instruction-following capabilities in scientific domains is essential for effectively leveraging Multimodal Large Language Models (MLLMs
arXiv:2505.23022v2 Announce Type: replace Abstract: Large Language Model (LLM) serving increasingly underpins online Web services such as conversational agents, Web search, and programming assistants,
arXiv:2608.25168v1 Announce Type: new Abstract: In multi-view anomaly detection, more cross-view information can actually hurt. When multiple inspection views are naively fused in a reconstruction-bas
arXiv:2412.12660v2 Announce Type: replace Abstract: Recently, developing unified medical image segmentation models gains increasing attention, especially with the advent of the Segment Anything Model
arXiv:2603.16558v2 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) achieve strong performance on many multimodal tasks, but object hallucinations severely undermine their reliabi
arXiv:2608.25123v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves large language models by incorporating external knowledge without retraining, but existing methods often u
arXiv:2608.24920v1 Announce Type: new Abstract: This study examines whether LLM-generated replies remain semantically consistent when the underlying LLM changes. Using messages from real collaborative
arXiv:2608.25485v1 Announce Type: new Abstract: Vision-language models like CLIP have shown sig- nificant potential in handling natural images, yet their perfor- mance is often limited by the distinct
arXiv:2608.25162v1 Announce Type: new Abstract: Robotic object packing has been a core challenge for robotic deployment in logistics, industry, etc., due to the curse of dimensionality in combinatoria
arXiv:2608.25630v1 Announce Type: new Abstract: Volumetric medical VQA requires reasoning over long and redundant 3D visual token sequences, especially in multi-sequence MRI where complementary modali
Several articles, podcasts etc now about the Open AI Hugging Face incident, from reputable outlets, framing this as 'AI going rouge' & debating what AI did or didn't do. When can we shift to focusing
arXiv:2608.25068v1 Announce Type: new Abstract: Depth pruning removes entire Transformer blocks to reduce the inference cost of large language models, but disrupts the hidden-state distributions expec
arXiv:2608.25347v1 Announce Type: new Abstract: The Jacobian lens (J-lens) has been proposed as a way to read verbalizable representations from language models. However, its principle and meaning lack
arXiv:2608.25282v1 Announce Type: new Abstract: Mixed-Integer Linear Programming (MILP) is a fundamental optimization paradigm in combinatorial optimization and has been widely applied across real-wor
arXiv:2608.25246v1 Announce Type: new Abstract: Badminton is a compact but challenging domain for game AI: a player must choose a physically feasible shuttle trajectory, anticipate the opponent's inte