Search: “models”

I was somewhat disappointed with the performance of Qwen 3.8 Flash Next on my single RTX 5090 using llama.cpp. One issue is that llama.cpp still has no Expert Caching implemented for MoE models. There

What's Changed GET /api/show now advertises each model's thinking controls and default: curl http://localhost:11434/api/show -d '{'model': 'glm-5.3-flash:cloud'}' { 'thinking': { 'values': ['low', 'hi

I have always posted about budget builds on here, and often asked how we are going to run the next big models. Often Plenty of downvotes too or folks telling me that it's not running if I'm getting 5t

arXiv:2609.20575v1 Announce Type: cross Abstract: Learning visual policies for locomotion and manipulation requires coordinating contact with the environment and can incur substantial computation and

arXiv:2609.19519v1 Announce Type: new Abstract: Language-model agents are increasingly asked to carry out work spanning days or weeks, such as an operations remediation or a research programme. Such a

arXiv:2609.19969v1 Announce Type: new Abstract: The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost

arXiv:2604.02745v2 Announce Type: replace Abstract: Radar odometry is crucial for robust localization in challenging environments; however, the sparsity of reliable returns and distinctive noise chara

arXiv:2609.20278v1 Announce Type: cross Abstract: Text, knowledge graphs, and hypergraphs all have elements that play distinct roles within relation instances, structure that is lost when data is flat

arXiv:2609.20543v1 Announce Type: new Abstract: Full-consensus rates are often treated as indicators of collective cognition, yet depend on how participation and final states are operationalized. We r

arXiv:2609.20389v1 Announce Type: cross Abstract: Offline policy evaluation (OPE) is crucial in high-stakes reinforcement learning applications, where new policies must be assessed reliably before dep

arXiv:2609.19154v1 Announce Type: new Abstract: While Large Language Models (LLMs) achieve high accuracy on established Classical Chinese Poetry benchmarks, it remains challenging to distinguish trans

arXiv:2609.19290v1 Announce Type: cross Abstract: Clinical decision-making for coronary intervention relies mainly on angiography and fractional flow reserve (FFR). However, angiography is two-dimensi

I've been running Qwen3.8-Flash-Next as my main local coding model from past few weeks. The file is 95.5 GiB and my Mac has 64 GB. It works because the routed experts stay on SSD and only get read whe

arXiv:2609.19204v1 Announce Type: cross Abstract: Robotic systems operating in dynamic environments require visual perception that evolves continuously with the incoming sensory stream. Event cameras

Super interesting work from Zoom and colleagues. If you maintain a hand-built coding harness, there are some great insights here. (bookmark it) They held the execution loop of a coding harness fixed a

arXiv:2609.19613v1 Announce Type: cross Abstract: Dexterous food manipulation requires control under deformation, occlusion, and uncertain contact. We present TacSushi, a tactile-grounded, Cosmos3-bas

arXiv:2609.19600v1 Announce Type: new Abstract: Adapting robots to new objects and tasks requires interaction experience that can be costly to obtain. We present WorldContact, a contact-centric world

arXiv:2603.28662v2 Announce Type: replace-cross Abstract: Agentic vision-language models increasingly act through extended interactions, but most evaluations still focus on single-image, single-turn c

arXiv:2609.18736v1 Announce Type: new Abstract: Despite recent advances in large language models (LLMs), performing logically consistent deductive reasoning over extended interactions remains challeng

arXiv:2609.18038v1 Announce Type: new Abstract: The world population is growing rapidly, and technology is improving in parallel. Meeting the huge demand for food for these 7 billion people not only d

arXiv:2609.17613v1 Announce Type: new Abstract: Zero-shot object counting aims to estimate the number of objects specified by a text query without category-specific training. Recent approaches primari

arXiv:2609.19124v1 Announce Type: new Abstract: Emergent coordinated behaviors of AI agents are starting to present critical safety risks. A key phenomenon driving these behaviors is the rapid formati

arXiv:2609.18766v1 Announce Type: cross Abstract: Large audio-language models have shown promise for anti-fraud detection by directly processing speech and reasoning over fraud-related evidence. Their

arXiv:2602.02888v2 Announce Type: replace-cross Abstract: Hallucinations remain a major obstacle for large language models (LLMs), especially in safety-critical domains. We present HALT (Hallucination

arXiv:2609.18622v1 Announce Type: new Abstract: Classifiers can make identical predictions yet require labels to compare their selective performance: confidence ranks weight the same errors differentl

arXiv:2609.18106v1 Announce Type: cross Abstract: Open-weight large language models are rapidly entering hiring pipelines, yet their discriminatory failure modes -- and the regulatory exposure these c

arXiv:2609.17763v1 Announce Type: new Abstract: Next-day wildfire prediction requires models whose forecasts can be evaluated alongside the assumptions and historical evidence used in their computatio

arXiv:2412.00176v4 Announce Type: replace Abstract: We explore whether pre-training on datasets with paintings is necessary for a model to learn an artistic style with only a few examples. To investig

arXiv:2609.17728v1 Announce Type: new Abstract: Recent Vision-Language-Action (VLA) models for autonomous driving have incorporated world modeling by predicting future driving scenes alongside driving

arXiv:2609.18844v1 Announce Type: new Abstract: Multimodal coding agents are expected to turn visual inputs into usable artifacts, and they act through a harness, the layer of tools, context managemen

arXiv:2609.18037v1 Announce Type: new Abstract: Segment Anything Models provide reusable priors, yet they require user prompts and cannot support fully automatic instrument segmentation. Automatic pro

arXiv:2601.23232v4 Announce Type: replace-cross Abstract: In recent years, large language models (LLMs) have made rapid progress in information retrieval, yet existing research has mainly focused on t

arXiv:2609.18642v1 Announce Type: new Abstract: Large language models (LLMs) often suffer from capability stagnation in self-improvement training because fixed difficulty levels fail to adapt to their

arXiv:2609.18174v1 Announce Type: new Abstract: Dexterous in-hand manipulation requires policies that coordinate high-DoF hand joints through intermittent, contact-rich interaction. Beyond target-orie

arXiv:2609.18958v1 Announce Type: cross Abstract: The natural way to review a long recording or document with a multimodal model is to hand it the raw source and ask for a review in one call. We show

arXiv:2609.17984v1 Announce Type: new Abstract: Machine-learning libraries such as Weka and scikit-learn were designed for human programmers. Language-model agents now use these same libraries by reca

arXiv:2609.18182v1 Announce Type: new Abstract: Real-world agents fundamentally require persistent non-parametric knowledge for dynamic reasoning, i.e., long-term memory and retrieval-augmented genera

arXiv:2609.16309v1 Announce Type: new Abstract: Despite the rapid progress of LLM-based agents for planning, code generation, and debugging, their practical value for tabular machine learning remains

arXiv:2609.16948v1 Announce Type: new Abstract: Near-field to far-field transformation is central to large-aperture antenna testing, yet two coupled challenges remain: costly phase acquisition at mill

metal: fix NaN in mul_mm_id when activations exceed f16 range (#26223) test-backend-ops: reproduce MUL_MAT_ID NaN for activations beyond f16 The Metal mul_mm_id path narrows src1 to half for the simdg

arXiv:2609.16664v1 Announce Type: new Abstract: Leveraging Large Vision-Language Models like CLIP has recently set new benchmarks for No-Reference Image Quality Assessment (NR-IQA). However, the contr

arXiv:2609.16814v1 Announce Type: new Abstract: While Large Language Model (LLM)-based Natural Language Inference (NLI) systems achieve high accuracy, their decision-making processes lack auditable st

arXiv:2609.16204v1 Announce Type: cross Abstract: Safety guardrails in open-weight language models can be readily bypassed using Refusal Feature Ablation (RFA), a technique that identifies and project

arXiv:2609.17210v1 Announce Type: cross Abstract: Vision-language-action (VLA) models, world-action models (WAMs), and offline reinforcement learning methods are rapidly expanding the design space of

arXiv:2603.12264v2 Announce Type: replace Abstract: Unified multimodal models target joint understanding, reasoning, and generation, but current image editing benchmarks are largely confined to natura

arXiv:2609.16816v1 Announce Type: cross Abstract: Language model-generated rubrics are increasingly used as reward signals for rubric-based reinforcement learning, LLM-as-a-judge evaluation, and autom