TiCo: Time-Controllable Spoken Dialogue Model
arXiv:2603.22267v2 Announce Type: replace-cross Abstract: We introduce TiCo, a time-controllable spoken dialogue model (SDM) that follows time-constrained instructions (e.g., 'Please generate a respon
Knowledge catalogue
arXiv:2603.22267v2 Announce Type: replace-cross Abstract: We introduce TiCo, a time-controllable spoken dialogue model (SDM) that follows time-constrained instructions (e.g., 'Please generate a respon
arXiv:2509.15642v3 Announce Type: replace Abstract: Joint RGB-infrared perception is essential for achieving robustness under diverse weather and illumination conditions. Although foundation models ex
arXiv:2605.11255v1 Announce Type: new Abstract: We present Hebatron, a Hebrew-specialized open-weight large language model built on the NVIDIA Nemotron-3 sparse Mixture-of-Experts architecture. Traini
arXiv:2605.11061v1 Announce Type: new Abstract: The evolution of visual generative models has long been constrained by fragmented architectures relying on disjoint text encoders and external VAEs. In
arXiv:2605.11301v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have heterogeneous strengths across OCR, chart understanding, spatial reasoning, visual question answering, c
arXiv:2605.10817v1 Announce Type: new Abstract: Clinical EEG interpretation requires reasoning over full EEG sessions and integrating signal patterns with clinical context. Existing EEG foundation mod
arXiv:2605.09269v1 Announce Type: new Abstract: Aligning Multimodal Large Language Models (MLLMs) requires reliable reward models, yet existing single-step evaluators can suffer from lazy judging, exp
arXiv:2605.09832v1 Announce Type: new Abstract: Knowledge of a protein's atomic conformational ensemble is critical to determining its function, yet state-of-the-art ensemble prediction models are lim
TabPFN-3 is a pre-trained tabular foundation model that supports datasets up to 1,000,000 rows × 200 features , representing a significant scaling improvement for the TabPFN family. The model delivers
arXiv:2605.09519v1 Announce Type: new Abstract: We introduce the concept of weighted rules under the stable model semantics following the log-linear models of Markov Logic. This provides versatile met
arXiv:2511.18085v4 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models show promising knowledge accumulation ability from pretraining, yet continual learning in VLA remains chal
arXiv:2605.07319v1 Announce Type: cross Abstract: We introduce Flux Matching, a new paradigm for generative modeling that generalizes existing score-based models to a broader family of vector fields t
Give our early preview of Computer Use (with ANY model) a try today! Built into the latest Hermes Agent and powered by @trycua - opens the door to any model, not just the frontier models in special mo
arXiv:2605.07520v1 Announce Type: new Abstract: Differentiable planning enables gradient-based optimization of decision-making problems by leveraging differentiable models of system dynamics. However,
arXiv:2605.06728v1 Announce Type: cross Abstract: Interpreting transcriptomic data is one of the most common analytical tasks in modern biology. Yet most current models either consume expression profi
arXiv:2605.06898v1 Announce Type: new Abstract: At the heart of existing language model agents is a fixed orchestrator program responsible for the state transition between consecutive turns. This pape
arXiv:2603.11911v3 Announce Type: replace Abstract: We present InSpatio-WorldFM, an open-source real-time frame model for spatial intelligence. Unlike video-based world models that rely on sequential
arXiv:2605.05049v1 Announce Type: cross Abstract: Frontier models increasingly adopt Mixture-of-Experts (MoE) architectures to achieve large-model performance at reduced cost. However, training MoE mo
arXiv:2506.19714v2 Announce Type: replace-cross Abstract: Offline model-based optimization (MBO) refers to the task of optimizing a black-box objective function using only a fixed set of prior input-o
arXiv:2506.08849v4 Announce Type: replace Abstract: Vision-Language Foundation Models (VLFMs) exhibit remarkable generalization, yet their direct application to medical ultrasound is severely hindered
arXiv:2601.08116v2 Announce Type: replace Abstract: Tropical cyclones are dangerous natural hazards, but their hazard is challenging to quantify directly from historical datasets due to limited datase
arXiv:2605.02714v1 Announce Type: new Abstract: The advent of foundation models has heralded a new era in medical artificial intelligence (AI), enabling the extraction of generalizable representations
arXiv:2602.11543v2 Announce Type: replace Abstract: Pretraining large language models (LLMs) typically requires centralized clusters with thousands of high-memory GPUs (e.g., H100/A100). Recent decent
arXiv:2604.28196v1 Announce Type: new Abstract: Driving world models serve as a pivotal technology for autonomous driving by simulating environmental dynamics. However, existing approaches predominant
arXiv:2604.27351v1 Announce Type: new Abstract: Agentic large language model systems have demonstrated strong capabilities. However, their reliance on language as the universal interface fundamentally
arXiv:2604.27093v1 Announce Type: cross Abstract: Current LLM safety alignment techniques improve model robustness against adversarial attacks, but overlook whether and how LLMs can recover helpfulnes
arXiv:2604.28185v1 Announce Type: new Abstract: Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still str
arXiv:2604.27082v1 Announce Type: new Abstract: We present a framework for migrating production Large Language Model (LLM) based systems when the underlying model reaches end-of-life or requires repla
Increasingly, I think, we will see a gap between what you can do with frontier model APIs & what you can do with the native apps from the frontier labs (Codex, Claude Code). Models developed and train
OpenAI is preparing to launch a new frontier cybersecurity model, GPT-5.5-Cyber. CEO Sam Altman said the model will not be available to the general public, but will be first rolled out to a select gro
$3/million output tokens. Qwen 3.5 Plus is basically a frontier model. Let that sink in. Introducing Qwen3.6-Plus from @Alibaba_Qwen, a 1M-context model built for real-world agents, agentic coding, an
arXiv:2604.25200v1 Announce Type: cross Abstract: Public agencies are beginning to consider large language models (LLMs) as decision-support tools for grant evaluation. This creates a practical govern
arXiv:2604.25685v1 Announce Type: cross Abstract: Foundation segmentation models such as the Segment Anything Model (SAM) have demonstrated strong generalization across natural images; however, their
arXiv:2604.25781v1 Announce Type: new Abstract: Articulation modeling aims to infer movable parts and their motion parameters for a 3D object, enabling interactive animation, simulation, and shape edi
arXiv:2603.19124v2 Announce Type: replace Abstract: This paper presents the design, modeling, and fabrication of 3D-printed, tendon-actuated continuum robots featuring a flexible, tapered backbone con
'If they ever tell my story let them say that I walked with giants'--Troy I am humbled&excited the model we released last week is trending #2 on @huggingface, between giant models such as DeepSeek,Qwe
arXiv:2604.22823v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) rely on multimodal pre-training over diverse data sources, where different datasets often induce complementar
Results on the remainder of our benchmarks are in for Kimi K2.6, the new #1 open-weight model on the Vals Index (#8 overall) Kimi K2.6 is competitive with many closed-weight models, at a fraction of t
arXiv:2604.22748v1 Announce Type: new Abstract: As AI systems move from generating text to accomplishing goals through sustained interaction, the ability to model environment dynamics becomes a centra
Here's a uv one-liner that downloads and runs the MLX model against a local mp3 file uv run --with mlx-audio python -m mlx_audio.stt.generate --model mlx-community/VibeVoice-ASR-4bit --audio lenny.mp3
arXiv:2604.22230v1 Announce Type: cross Abstract: Benchmark hacking refers to tuning a machine learning model to score highly on certain evaluation criteria without improving true generalization or fa
arXiv:2604.22464v1 Announce Type: new Abstract: Continual Model Merging (CMM) sequentially integrates task-specific models into a unified architecture without intensive retraining. However, existing C
No more updating needed for new model releases via Nous Portal and OpenRouter! Hermes will no longer have to be updated to receive model list curation updates for several providers, including Nous Por
API is Available Today! 🔹 Keep base_url, just update model to deepseek-v4-pro or deepseek-v4-flash. 🔹 Supports OpenAI ChatCompletions & Anthropic APIs. 🔹 Both models support 1M context & dual modes (T
deepseek-v4-flash is now available on Ollama's cloud! Hosted in the US. Try it with Claude Code: ollama launch claude --model deepseek-v4-flash:cloud Try it with OpenClaw: ollama launch openclaw --mod
arXiv:2508.19353v2 Announce Type: replace-cross Abstract: While transfer learning is an effective strategy, it often overlooks the opportunity to leverage knowledge from numerous available models onli
arXiv:2604.21127v1 Announce Type: new Abstract: The NASA PACE mission provides unprecedented hyperspectral observations of ocean color, aerosols, and clouds, offering new insights into how these compo
arXiv:2507.01829v2 Announce Type: replace-cross Abstract: Multi-timescale sequence modeling relies on capturing both local fast dynamics and global slow context; yet, maintaining these capabilities un
arXiv:2604.20867v1 Announce Type: cross Abstract: Recent events surrounding the relationship between frontier AI suppliers and national-security customers have made a structural problem newly visible:
arXiv:2604.21052v1 Announce Type: cross Abstract: We build on the Visual Autoregressive Modeling (VAR) framework and formulate style transfer as conditional discrete sequence modeling in a learned lat
arXiv:2604.21223v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their ability to generate human-like text has ra
Sam Altman announced upcoming new features for Codex, OpenAI's code generation model, bundled with a new model release. The post suggests these features represent a significant expansion of Codex capa
arXiv:2604.20263v1 Announce Type: cross Abstract: Virtual cell modeling predicts molecular state changes under genetic perturbations in silico, which is essential for biological mechanism studies. How
arXiv:2509.25844v3 Announce Type: replace Abstract: When people query Vision-Language Models (VLMs) but cannot see the accompanying visual context (e.g. for blind and low-vision users), augmenting VLM
arXiv:2604.20796v1 Announce Type: new Abstract: We present LLaDA2.0-Uni, a unified discrete diffusion large language model (dLLM) that supports multimodal understanding and generation within a nativel
arXiv:2604.20111v1 Announce Type: cross Abstract: Sparse additive models have attracted much attention in high-dimensional data analysis due to their flexible representation and strong interpretabilit
arXiv:2511.14311v2 Announce Type: replace-cross Abstract: Model Predictive Control (MPC) has established itself as the primary methodology for constrained control, enabling autonomy across diverse app
OpenAI just announced its new GPT-5.5 model, which the company calls its 'smartest and most intuitive to use model yet, and the next step toward a new way of getting work done on a computer.' OpenAI j
arXiv:2604.20834v1 Announce Type: new Abstract: Recent advances in Vision-Language-Action (VLA) models have opened new avenues for robot manipulation, yet existing methods exhibit limited efficiency a
arXiv:2604.20127v1 Announce Type: new Abstract: Failures in complex systems often emerge through gradual degradation and the propagation of stress across interacting components rather than through iso