Knowledge catalogue
Today, together with @kyutai_labs, we’re introducing our new Audio-to-MIDI model. It takes a finished recording, identifies the instruments playing, and returns separate MIDI tracks for each — voice,
arXiv:2505.10946v3 Announce Type: replace-cross Abstract: Token communications (TokenCom) is an emerging generative semantic communication paradigm, where tokens serve as compact representation units
arXiv:2607.08395v1 Announce Type: cross Abstract: Persistent AI agents extend large language models (LLMs) beyond single-turn interaction into long-lived software systems. Unlike traditional chat assi
Token usage beginning to tip towards open models. Ollama’s @jmorgan and Peter Fenton predict that a supermajority of tokens in the future will be from open models. Is compute scarcity masking the real
arXiv:2607.08010v1 Announce Type: new Abstract: Production LLM agents often waste latency and reliability by regenerating code for the same procedural steps on every request. We replace this inference
arXiv:2510.04100v2 Announce Type: replace-cross Abstract: Topological mapping offers a compact and robust representation for navigation, but progress in the field is hindered by the lack of standardiz
arXiv:2607.08057v1 Announce Type: cross Abstract: Despite the rapid advancements of large language models (LLMs), LLM serving systems remain memory-intensive and costly. The key-value (KV) cache, whic
arXiv:2602.04718v2 Announce Type: replace-cross Abstract: A central premise in mechanistic interpretability is that meaningful concepts in language models are represented by linear features in activat
arXiv:2607.08393v1 Announce Type: new Abstract: Fine-tuning LLMs to inject new knowledge faces a critical challenge: LLMs can quickly memorize new facts, yet fail to use them for downstream reasoning
arXiv:2607.08602v1 Announce Type: new Abstract: Hepatocellular carcinoma (HCC) is a common malignancy and a leading cause of cancer-related mortality. Current guidelines and staging systems provide co
arXiv:2607.07958v1 Announce Type: new Abstract: Hand spasticity and resulting pain affect 12 million people worldwide, including stroke survivors, arthritis patients, and those with other muscle and n
arXiv:2607.07716v1 Announce Type: cross Abstract: Temporal graphs are ubiquitous in real-world applications and Temporal Graph Networks (TGNs) have achieved superior predictive accuracy. Understanding
arXiv:2607.08400v1 Announce Type: cross Abstract: LLM agents reach users through resellers, who may rebrand a developer's agent or substitute a cheaper model. When provenance is disputed, attribution
Vercel has added Tree and Waterfall view options to its Traces feature, providing developers with enhanced visualization tools for analyzing application performance and request flows. These new view m
arXiv:2607.08408v1 Announce Type: cross Abstract: Gaussian splatting is the current state-of-the-art for dense, deformable 3D anatomy reconstruction in robot-assisted minimally invasive surgery (RAMIS
arXiv:2511.07624v3 Announce Type: replace Abstract: Markerless motion tracking has advanced rapidly in the past 10 years and currently offers powerful opportunities for behavioural, clinical, and biom
arXiv:2606.16447v2 Announce Type: replace-cross Abstract: Imitation learning has enabled highly-dexterous robotic manipulation from RGB observations. Policies trained with these methods, however, typi
arXiv:2511.15060v2 Announce Type: replace-cross Abstract: Total variation (TV) regularization is a classical edge-preserving technique widely used across image recovery and reconstruction problems; ho
arXiv:2602.01385v2 Announce Type: replace Abstract: Triphibious robots capable of multi-domain motion and cross-domain transitions are promising to handle complex tasks across diverse environments. Ho
arXiv:2602.23440v4 Announce Type: replace Abstract: Reinforcement learning has emerged as an effective paradigm for training large language models to interleave reasoning with search engine calls. How
arXiv:2607.07762v1 Announce Type: new Abstract: Modern machine learning (ML) increasingly relies on complex models whose behavior is difficult to characterize beyond empirical performance metrics. Acr
Try Grok 4.5 in Perplexity Grok 4.5 is now available as an orchestrator model in Computer for Consumer Pro and Max subscribers. We evaluated it against five other orchestrator configurations on WANDR.
arXiv:2607.08124v1 Announce Type: cross Abstract: The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context,
arXiv:2607.08370v1 Announce Type: cross Abstract: We derive bounds for the volume of tubular neighbourhoods of smooth Pfaffian hypersurfaces, generalising known results for algebraic varieties. The bo
arXiv:2511.02036v5 Announce Type: replace Abstract: In real-time Visual SLAM systems, local mapping must operate under strict latency constraints, as delays degrade map quality and increase the risk o
arXiv:2607.08236v1 Announce Type: new Abstract: Event-based lip reading has recently emerged as a promising direction for visual speech recognition, benefiting from the high temporal resolution and mo
arXiv:2607.08456v1 Announce Type: cross Abstract: A model should refuse two different things: answers it would get wrong, and questions it should not answer at all, such as unanswerable ones or ones r
This post discusses two underutilized capabilities of OpenAI's Codex: mid-process steering (the ability to guide code generation in real-time during execution) and computer use functionality. The auth
arXiv:2607.08339v1 Announce Type: cross Abstract: State-of-the-art code models achieve impressive performance, yet the extent to which they internally encode type information remains poorly understood
Typical NYT understatement for what is an apocalyptic destruction of the American innovation ecosystem. I can't understand how the Trump administration is doing this while boasting about American tech
arXiv:2607.08075v1 Announce Type: new Abstract: Unmanned Aerial Vehicle (UAV) videos are widely used in traffic monitoring, urban management, and emergency rescue. However, existing UAV video percepti
arXiv:2607.08646v1 Announce Type: cross Abstract: As available training data approaches its physical limit, gains from Scaling Laws have begun to diminish. Consequently, improving Large Language Model
arXiv:2607.07724v1 Announce Type: cross Abstract: Block-sparse attention scales long-context language models by replacing the O(N^2) softmax with a per-query top-k selection over key blocks. This cuto
arXiv:2607.08127v1 Announce Type: new Abstract: Generative video foundation models exhibit strong compositional priors, yet world-action models (WAMs) and video-action models (VAMs) often lose these p
arXiv:2607.08284v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated rapidly improving long-context capabilities, prompting a wave of benchmarks designed to evaluate them. Ho
arXiv:2607.08170v1 Announce Type: new Abstract: Zero-shot model size interpolation aims to create new models of intermediate target sizes by combining existing models without additional training. Rece
arXiv:2607.08768v1 Announce Type: new Abstract: The rapid development of large language models and multimodal large language models has accelerated the emergence of proactive agents capable of operati
arXiv:2607.08156v1 Announce Type: new Abstract: The growing applications of facial recognition systems are accompanied by increasingly diverse security threats. Existing datasets lack detailed textual
arXiv:2607.08267v1 Announce Type: new Abstract: Unmanned aerial vehicles (UAVs) increasingly rely on visual grounding capabilities to localize task-relevant targets from diverse instructions in comple
arXiv:2607.08007v1 Announce Type: cross Abstract: Galvanic skin response (GSR) is widely used for stress detection, but wrist-based GSR remains challenging because its absolute amplitude can differ su
arXiv:2607.07763v1 Announce Type: new Abstract: World models are typically trained to predict discrete-time physical dynamics with a fixed step size baked into the model weights, preventing prediction
arXiv:2607.08198v1 Announce Type: new Abstract: This paper studies the problem of learning a joint distribution from marginal observations, which is inherently ill-posed due to the ambiguity of feasib
arXiv:2607.07772v1 Announce Type: new Abstract: In this age of social media, sites like Twitter have become meeting places for people to share their views and feelings on a wide range of issues and cu
arXiv:2607.08748v1 Announce Type: new Abstract: In this study, we present a large-scale descriptive analysis of the use of an AI-based learning assistant (Syntea) in higher education. Based on objecti
arXiv:2508.09767v3 Announce Type: replace-cross Abstract: We propose UtterTune, a lightweight method for adapting a multilingual text-to-speech (TTS) system built on a large language model (LLM). It i
The search results do not contain specific information about v0.32.0-rc0. Based on the version numbering and context from Ollama's release patterns, v0.32.0-rc0 is a release candidate for Ollama, a la
arXiv:2607.07915v1 Announce Type: cross Abstract: Large language models (LLMs) are reshaping social science methodology. Researchers increasingly prompt language models to generate quantitative measur
arXiv:2607.08731v1 Announce Type: cross Abstract: A national language model offers a linguistic community its own instrument for measuring what its citizens say and value. Portugal's AMALIA, a publicl
Valve has introduced new verification systems for its upcoming Steam Machine and Steam Frame hardware, detailed at GDC 2026 . Steam Machine Verified functions as a higher-performance extension of Stea
arXiv:2607.08104v1 Announce Type: new Abstract: Stochastic gradient descent (SGD) is a cornerstone of modern optimization. While its performance under heavy-tailed noise is often addressed through spe
arXiv:2603.18078v2 Announce Type: replace Abstract: We present the Variational Phasor Circuit (VPC), a deterministic classical learning architecture on the continuous S^1 unit-circle manifold. Inspire
As AI infrastructure investment scales globally and inference workloads multiply, cache storage is emerging as the critical data layer that makes AI factories functional, persistent and economically v
arXiv:2607.07846v1 Announce Type: new Abstract: VectorizationLLM is a specialized Large Language Model based on Google open-weight LLMs. The model is designed to assist students to learn smart vectori
arXiv:2607.08489v1 Announce Type: cross Abstract: Vision-language models excel at video captioning, yet typically generate descriptions that fail to capture individual viewers' attention. We propose V
arXiv:2511.20644v2 Announce Type: replace Abstract: Spatial reasoning is a critical capability for intelligent robots, yet current vision-language models (VLMs) still fall short of human-level perform
arXiv:2607.08541v1 Announce Type: cross Abstract: Open-vocabulary object detection and segmentation aim to recognize arbitrary objects beyond predefined categories. Although recent vision-language and
Volkswagen CEO Oliver Blume presented a comprehensive restructuring plan to the supervisory board aimed at making the group more robust and competitive in a challenging environment. The plan reportedl
arXiv:2607.08112v1 Announce Type: new Abstract: We introduce VSRo-200, the first large-scale dataset for visual speech recognition (lip reading) in Romanian, comprising 200 hours of real-world podcast
arXiv:2607.08729v1 Announce Type: new Abstract: Multi-object tracking (MOT) has achieved strong performance on benchmarks dominated by short video sequences. However, such datasets do not adequately e
arXiv:2607.08772v1 Announce Type: new Abstract: Estimating 3D geometry in underwater environments presents unique challenges due to light attenuation, scattering, and the absence of large-scale, high-