Search: “models”

Two months ago I announced I had found a new dynamic quant method called Voodoo Quant which was SOTA for the most aggressive quant levels on some smaller Qwen3.5 GGUF models. I kept the methodology pr

arXiv:2609.12660v1 Announce Type: new Abstract: This paper presents a Model Predictive Control-based motion planning and control pipeline for autonomous car racing capable of adapting to different dri

arXiv:2609.13024v1 Announce Type: new Abstract: As a key model compression technique, knowledge distillation aims to transfer knowledge from a high-capacity teacher model to a lightweight student mode

arXiv:2609.12850v1 Announce Type: new Abstract: Accurate head modeling requires a stable yet expressive geometric representation. Existing Gaussian-based head avatars commonly rely on parametric templ

arXiv:2609.12913v1 Announce Type: new Abstract: Dense retrieval systems increasingly rely on multi-billion-parameter language models, whose memory and computational requirements make large-scale index

arXiv:2501.04234v2 Announce Type: replace-cross Abstract: Modern artificial intelligence is supported by machine learning models (e.g., foundation models) that are pretrained on a massive data corpus

arXiv:2609.12591v1 Announce Type: new Abstract: Foundation models are increasingly adapted through fine-tuning, model editing, and alignment procedures while retaining previously acquired capabilities

Just stumbled upon this. Seems to be a new 3B TTS model mainly focused on Indian languages (22 Indic languages + English). Apparently supports code-switching, romanized text, emotion/delivery control

arXiv:2609.11365v1 Announce Type: new Abstract: In shared-genome language-model societies, restricted evidence visibility favors reusable, value-indexed latent packet interfaces, whereas the sole high

arXiv:2609.10810v1 Announce Type: new Abstract: Minimal-edit Grammatical Error Correction (GEC) is a challenging task for zero- and few-shot prompted Large Language Models (LLMs), which systematically

arXiv:2609.11871v1 Announce Type: new Abstract: Agent-based model predictive control (AMPC) has recently been proposed as a distributed scheme that collaborates with all agents to achieve optimal holi

arXiv:2508.05830v3 Announce Type: replace Abstract: Large Language Model (LLM) studies that use language responses elicited from depression assessments to predict scores on those same assessments ofte

arXiv:2609.11133v1 Announce Type: new Abstract: Datacenter GPU power is the binding constraint on LLM serving capacity, and production serving has shifted to prefill/decode (PD) disaggregation. Deploy

arXiv:2609.11752v1 Announce Type: cross Abstract: For industrial content risk control, the real deployment constraint is not average accuracy but how much risk can be auto-handled under high precision

After noticing that it is ranked among MUCH larger frontier models in the EQ-Bench Creative Writing benchmark and the Hemingway-bench, I decided to give it a try and was very impressed. I didn't do ve

arXiv:2609.08606v1 Announce Type: cross Abstract: Subseasonal-to-seasonal (S2S) forecasting is societally critical, supporting decision-making in sectors ranging from water and agricultural management

arXiv:2609.09985v1 Announce Type: new Abstract: Real-world video understanding requires integrating visual, audio, textual, and temporal evidence distributed across a video. Yet many pipelines use a f

arXiv:2609.06984v1 Announce Type: new Abstract: Atrial fibrillation (AF) is the most common cardiac arrhythmia and is associated with increased risks of stroke and heart failure. The growing availabil

arXiv:2609.07986v1 Announce Type: new Abstract: Purpose: Accurate CT protocol selection is critical for diagnostic quality and patient safety, yet the current process is manual, time-consuming, and pr

arXiv:2503.13938v3 Announce Type: replace Abstract: Comprehensive traffic scene understanding is a foundational capability for Intelligent Transportation Systems (ITS) underpinning applications such a

arXiv:2609.05832v1 Announce Type: new Abstract: Integrating visuomotor policies or Vision-Language-Action (VLA) models with force/torque (F/T) perception has demonstrated significant progress in imita

arXiv:2609.07874v1 Announce Type: new Abstract: Multimodal large language models often capture visual-linguistic correlations but struggle to predict how local visual interventions propagate and affec

Machine learning doesn't end when the model is trained. You still need to evaluate it, deploy it, and build the infrastructure to keep it working in production. Today's Deal of the Day takes you acros

arXiv:2609.09062v1 Announce Type: new Abstract: We present a real-world case study of multi-task learning (MTL) for temporal process modeling from limited data with temporally sparse labels. Specifica

arXiv:2609.08618v1 Announce Type: new Abstract: Benchmark scores describe what a checkpoint can do now, but they do not determine how it will respond to the next training episode. We measure this miss

arXiv:2609.06785v1 Announce Type: new Abstract: Out-of-Distribution (OOD) detection remains a fundamental challenge for neural networks, whose predictions can be overconfident on inputs that deviate f

I was reading up on the recent controversy around Tristan Buckmaster, Levent Alpöge, OpenAI, and the Navier–Stokes result, and it got me thinking about something broader than this particular dispute.

arXiv:2510.10075v2 Announce Type: replace-cross Abstract: Deep learning models have attracted lots of research attention in time series classification (TSC) task in the past two decades. Recently, dee

Note this is separate from privacy - you can make sure your data is not used for training by turning that off in OpenAI and Claude. You can also use an open weights model, but as they continue to impr

This is very similar to how we think about context management in Deep Agents: compaction should reduce what is sent to the model, not erase the underlying work history. In Deep Agents, the logic is: -

arXiv:2609.03887v1 Announce Type: new Abstract: How do the methods used to train language models to refuse harmful requests shape how that refusal actually works inside the model? We compare three pos

Building a Physical AI system takes a continuous pipeline, not a single training job. This post shows how to run that model factory (synthetic data generation, post-training, and closed-loop evaluatio

In controlled offline evaluations, HydraFusion’s selective coding workflows matched or exceeded the evaluated Opus 5 baseline while reducing estimated workflow cost. Now available as a research previe

arXiv:2609.04066v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) has emerged as a powerful yet sample-inefficient approach for learning reward models from human pref

arXiv:2609.02448v1 Announce Type: new Abstract: Digital elevation models (DEMs) can provide accurate height information, making it invaluable for analyzing the lunar surface. As the European Space Age

arXiv:2602.06504v2 Announce Type: replace-cross Abstract: Vision-based models for robotic grasping automate critical, repetitive, and draining industrial tasks. Existing approaches are typically limit

arXiv:2609.02366v1 Announce Type: cross Abstract: Named Entity Recognition (NER) has achieved substantial progress since the advent of large language models (LLMs). Nevertheless, the recognition of lo

Sam Sabin / Axios: OpenAI commits 1B in subsidized model access, training, support, and partnerships to a new initiative aimed at protecting essential services around the world — - The 1 billion will

arXiv:2609.02377v1 Announce Type: new Abstract: High-resolution Synthetic Aperture Radar (SAR) imagery is critical for precision analysis such as automatic target recognition, yet its acquisition is c

Enterprises need practical solutions when it comes to artificial intelligence implementation. As organizations look to move AI projects from proof of concept into production, navigating the challenges

arXiv:2609.02499v1 Announce Type: cross Abstract: Recommender-system experiments often rely on a single random training seed, assuming that run-to-run stochasticity has limited impact on evaluation co

arXiv:2601.07795v2 Announce Type: replace Abstract: The European Space Agency (ESA), driven by its ambitions on planned lunar missions with the Argonaut lander, has a profound interest in reliable cra

arXiv:2609.00847v1 Announce Type: cross Abstract: As machine learning and artificial intelligence find their way into nearly every aspect of climate, weather, and Earth system modeling, it is worth pa

arXiv:2505.12781v5 Announce Type: replace-cross Abstract: Training high-performing Small Language Models (SLMs) remains costly, even with knowledge distillation and pruning from larger teacher models.

arXiv:2609.00798v1 Announce Type: new Abstract: Pixel-space diffusion has recently emerged as a promising direction for high-fidelity image generation by modeling images directly in the original pixel

arXiv:2609.00662v1 Announce Type: new Abstract: A multi-model language service must route each request while preserving workload-level budgets for compute, latency, memory, or monetary cost. Two featu