I built Ninfer 4080 for 16GB class GPUs
Hi everyone, TL/DR I created NInfer 4080 to run ISTA-DASLab-Qwen-3.8-27B-GSQ at 100k context on an RTX 4080 16GB GPU using way more of the hardware capabilities (max overall: 2720 tok/s prefill, 262 t
Knowledge catalogue
Hi everyone, TL/DR I created NInfer 4080 to run ISTA-DASLab-Qwen-3.8-27B-GSQ at 100k context on an RTX 4080 16GB GPU using way more of the hardware capabilities (max overall: 2720 tok/s prefill, 262 t
This is actually two models: Qwen Image 2.1 Fix v2.0 and Qwen Image 2.1 Fix Opinionated v1.0. The former surgically targets Qwen's weird noise and messy details with almost no effect on composition, a
arXiv:2610.00376v1 Announce Type: new Abstract: We evaluate Jev on ten dataset-defined application labels in CESNET-QUICEXT-25 using only the first ten packets' sizes, directions, and inter-packet tim
I mean , DeepSeek, Kimi, GLM, MiniMax -- the list of Chinese LLM's is such a long freaking list. As American's -- why don't we feel .. a little funny .. about being so far behind? Chinese entrepreneur
arXiv:2610.01692v1 Announce Type: new Abstract: Wrist electrodermal activity (EDA) differs in amplitude from one person to the next, so affect-recognition models normalize their input before classific
arXiv:2610.00092v1 Announce Type: cross Abstract: Data agents over structured sources must fit database schema into the model's context window. Large catalogs can span many databases and thousands of
arXiv:2610.00224v1 Announce Type: new Abstract: Building automation systems are increasingly represented as semantic knowledge graphs (KGs) using ontologies such as Brick and ASHRAE 223P, creating a m
arXiv:2610.01166v1 Announce Type: cross Abstract: Cardiovascular magnetic resonance (CMR), including cine imaging, is a reference standard for the noninvasive assessment of cardiac morphology and vent
arXiv:2610.01927v1 Announce Type: new Abstract: Feedforward foundation models have recently shown remarkable 3D reconstruction capabilities. However, existing models exhibit large tracking drift in lo
arXiv:2610.00234v1 Announce Type: new Abstract: 'Train a model on the same problems written under two incompatible conventions, both correct, and ask what the ordering of that data writes into the par
arXiv:2610.00890v1 Announce Type: cross Abstract: Coding agents often fail in the last mile: they build most of a feature but drop a requirement, test only the cases their implementation already handl
arXiv:2610.02044v1 Announce Type: new Abstract: Recent advances in rectified flow-based image-to-3D generative models have enabled high-fidelity 3D asset generation. Building on this, a growing line o
arXiv:2610.00582v1 Announce Type: new Abstract: Aesthetic image cropping aims to identify the optimal crop of an image in terms of aesthetics and composition. While supervision based on annotated data
arXiv:2610.00030v1 Announce Type: new Abstract: Object detection models often experience performance degradation when deployed under distribution shifts, caused by for example changes in weather type,
arXiv:2610.00610v1 Announce Type: cross Abstract: Explainable suicide-risk assessment requires models not only to estimate risk severity, but also to identify supporting language and the risk and prot
arXiv:2610.02140v1 Announce Type: cross Abstract: Introducing new capabilities to frontier models has long been the goal of posttraining, which predominantly employs supervised finetuning (SFT) and re
arXiv:2610.01358v1 Announce Type: cross Abstract: Single-particle cryo-electron microscopy (cryo-EM) has become a widely adopted technique for biomolecular structure determination. The conventional cr
arXiv:2610.01382v1 Announce Type: new Abstract: We introduce Gacha Decoding, an inference-time method for eliciting diverse language model generations that scales with model capability. Across open-en
arXiv:2610.00848v1 Announce Type: cross Abstract: Vision-language models (VLMs) have emerged as powerful candidates for universal vision backbones, with representative architectures including autoregr
arXiv:2610.00195v1 Announce Type: cross Abstract: Recent advances in Gaussian Splatting (GS) compression have enabled substantial reductions in GS model size. Reliable objective quality assessment is
arXiv:2610.00498v1 Announce Type: cross Abstract: When minimizing the squared-error loss, the popular CP decomposition can be interpreted as parameter inference in a Gaussian model with a low-rank mea
arXiv:2610.02197v1 Announce Type: new Abstract: Video generation models have achieved remarkable visual fidelity and have strong potential to become general-purpose world simulators. Despite this prog
**DISCLAIMER** THE PREFILLING TPS SHOWN ON THE PHONE IS COMPUTED ONLY FOR THE LAYERS IT HOLDS. ALREADY FIXING IT TO SHOW END-TO-END PREFILL RATE. NUMBERS BELOW ARE ACCURATE FOR E2E PREFILL RATE. Every
Ahmad Al‑Dahle joined Airbnb as CTO in January 2026 after leading Meta’s Llama generative‑AI models (2023–2025). He is steering an “inside‑out AI” strategy that deploys internal AI tools—such as the c
arXiv:2610.00074v1 Announce Type: new Abstract: K-Dense BYOK (bring your own keys) is a free, open-source AI research assistant for scientists in any field that runs on the researcher's own computer.
arXiv:2610.02206v1 Announce Type: cross Abstract: LLMs are increasingly applied to cybersecurity workflows, where they are expected to translate analysts' intent into tool invocations. However, existi
arXiv:2610.00609v1 Announce Type: new Abstract: Legal research is a core and time-consuming legal workflow. Lawyers must identify controlling authority, verify that it remains valid, reconcile statute
arXiv:2610.01153v1 Announce Type: cross Abstract: Looped Transformers introduce recurrent depth as a new scaling axis for LLMs: by repeatedly applying shared Transformer blocks, they increase effectiv
arXiv:2610.02038v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly combine reasoning, tool use, and action, but most evidence comes from episodic tasks with relatively imme
arXiv:2610.01058v1 Announce Type: cross Abstract: Quantized large language models are increasingly deployed on edge devices for their low latency and energy efficiency. However, model quantization wea
arXiv:2610.00860v1 Announce Type: cross Abstract: Background and Objectives: Fluorescence-labeled cellular arbors provide readouts of neuronal and microglial morphology, but fine and weakly labeled pr
arXiv:2610.01349v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents turn generated text into real side effects, so poisoned tool metadata, retrieved pages, memory, and reusa
arXiv:2610.00809v1 Announce Type: new Abstract: Vision-Language Models (VLMs) enable video annotation at scale, but costs accumulate quickly: processing a typical 60-second short-form video at one fra
arXiv:2610.01807v1 Announce Type: new Abstract: Reliable clinical deployment of deep medical image models is hindered by distribution shifts across scanners, sites, and acquisition protocols. Existing
arXiv:2610.00559v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have shown strong multimodal reasoning capabilities, yet whether they truly capture the physical consistency underlying re
arXiv:2610.01612v1 Announce Type: new Abstract: Continuous legged manipulation requires accurate end-effector tracking while the base keeps walking. Combining reinforcement learning (RL) with model pr
Row-Bot 5.0 is a major rebuild of the local-first AI assistant. The NiceGUI interface is gone, replaced by one React app across desktop, browsers, phones and tablets. The biggest change is how work is
arXiv:2610.01908v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves vision-language benchmark scores even without visual information during training. With im
arXiv:2610.00421v1 Announce Type: cross Abstract: Automated classification of brain tumors from MRI is a heavily published application of deep learning in medical imaging, with reported accuracies on
arXiv:2606.23595v2 Announce Type: replace Abstract: Language model reasoning can be substantially improved at test time via scaffolds that scale inference compute across different primitives -- sequen
arXiv:2610.02021v1 Announce Type: cross Abstract: Recent vision-language models (VLMs) exhibit remarkable generalization and reasoning abilities, yet 3D understanding in these models is limited by dat
arXiv:2610.01768v1 Announce Type: cross Abstract: With the increasing capabilities of Large-Language-Models (LLMs) and LLM-based agents, users are increasingly using them to solve everyday problems, s
This Week in Replit 1) Interactive charts are now in Replit chat. Why is this quarter's pipeline falling short? Which channels are performing best? Just ask Replit Agent 'let's visualize this' and get
arXiv:2610.01323v1 Announce Type: new Abstract: Safety-aligned large language models (LLMs) often refuse a harmful request but comply once the same goal is spread over several turns. Preference object
arXiv:2610.01243v1 Announce Type: cross Abstract: Vision-language models (VLMs) increasingly act as judges that pick the best of several generated images, so their choices decide what users see. Such
arXiv:2609.39810v1 Announce Type: new Abstract: Source-Free Universal Domain Adaptation (SF-UniDA) extends Universal Domain Adaptation by removing access to source data at adaptation time while still
arXiv:2609.39402v1 Announce Type: new Abstract: Value-model-free RLVR methods such as GRPO assign uniform advantages to all tokens in a rollout, ignoring that tokens contribute unequally. Recent metho
arXiv:2609.38652v1 Announce Type: new Abstract: Agentic AI systems increasingly rely on cloud-hosted large language models for planning, tool use, and iterative execution, raising concerns about API c
arXiv:2609.38954v1 Announce Type: cross Abstract: Large language model (LLM) agents could help security operations centers (SOCs) investigate advanced persistent threats (APTs) by turning weak leads i
arXiv:2609.39687v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) trains mathematical reasoning models using a privileged teacher that sees a reference solution and supervises student
arXiv:2609.39646v1 Announce Type: new Abstract: Federated learning faces severe communication bottlenecks when clients upload high-dimensional model updates. Existing methods often compress these upda
arXiv:2609.39005v1 Announce Type: new Abstract: Emergency managers need to know where floodwater is, how deep it is, and how it will change over the coming hours across an entire river basin. During a
arXiv:2609.38479v1 Announce Type: cross Abstract: This paper presents an explainable approach to pedestrian routing, in which perceived safety is estimated from street-level imagery through an explici
arXiv:2609.39250v1 Announce Type: new Abstract: Federated learning (FL) is a promising paradigm of machine learning, which preserves user privacy by enabling learning without sharing raw data with a c
arXiv:2609.39914v1 Announce Type: cross Abstract: Traditional simulations of parametric partial differential equations (PDEs) rely on repetitive computations for each parameter, which makes high-fidel
arXiv:2609.40324v1 Announce Type: new Abstract: We present Cogentic, a multi-agent harness for automated proof discovery on open research problems. While frontier language models can generate strong m
arXiv:2609.38368v1 Announce Type: new Abstract: Vision-language models (VLMs) increasingly reason over visual evidence that is cropped, segmented, retrieved, or revealed over time. Yet most VQA benchm
arXiv:2609.38222v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) can ground large language models in external evidence, but retrieved context does not guarantee that generated clai
arXiv:2609.38208v1 Announce Type: cross Abstract: Smoothed Particle Hydrodynamics (SPH) is well suited to a range of problems, particularly those involving large deformations in fluid dynamics. In rec
arXiv:2609.39584v1 Announce Type: cross Abstract: Edge computing has emerged as a critical computing paradigm in modern distributed systems by migrating data processing closer to end users and Interne