model releases

arXiv:2604.22192v1 Announce Type: new Abstract: Chart-to-code generation demands strict visual precision and syntactic correctness from Vision-Language Models (VLMs). However, existing approaches are

arXiv:2604.22313v1 Announce Type: new Abstract: NL2SQL systems deployed in industry settings often encounter ambiguous or unanswerable queries, particularly in interactive scenarios with incomplete us

arXiv:2604.22367v1 Announce Type: cross Abstract: Sign language research has achieved significant progress due to the advances in large language models (LLMs). However, the intrinsic ability of LLMs t

arXiv:2604.22294v1 Announce Type: cross Abstract: Real-world document question answering is challenging. Analysts must synthesize evidence across multiple documents and different parts of each documen

arXiv:2604.22499v1 Announce Type: new Abstract: Continuous estimation of high-dimensional finger kinematics from forearm surface electromyography (EMG) could enable natural control for hand prostheses

arXiv:2604.22496v1 Announce Type: new Abstract: In this study, deep learning is used to estimate kinetic parameters for modeling itaconic acid production based on real batch experiments conducted at d

DeepSeek V4-Pro is live on Fireworks: → Frontier-class coding and reasoning, open-weights → 1M context standard, MIT licensed → 1.74 / 3.48 per 1M tok Get started now → https://app.fireworks.ai/models

DeepSeek v4 Pro is now on Ollama's cloud! 🚀🚀🚀 Try it with Claude Code: ollama launch claude --model deepseek-v4-pro:cloud Try it with Hermes Agent: ollama launch hermes --model deepseek-v4-pro:cloud C

arXiv:2604.22606v1 Announce Type: new Abstract: Health misinformation remains one of the most pressing challenges on social media, particularly when cultural traditions intersect with scientific-sound

arXiv:2604.22515v1 Announce Type: new Abstract: Handwritten Arabic manuscripts preserve the Arab world's intellectual and cultural heritage, and writer identification supports provenance, authenticity

arXiv:2601.23022v3 Announce Type: replace Abstract: Aspect-Based Sentiment Analysis (ABSA) focuses on extracting sentiment at a fine-grained aspect level and has been widely applied across real-world

arXiv:2604.22413v1 Announce Type: cross Abstract: Graph Transformers can mix information globally, but this flexibility also creates failure modes: some tasks require long-range communication while ot

Doing the right thing might take time, but it’s worth the wait when tens of thousands of users’ production workloads depend on it. And yes, DeepSeek V4 is coming to @FireworksAI_HQ soon 👀🚀 The DeepSee

arXiv:2604.22036v1 Announce Type: cross Abstract: This paper introduces EgoMAGIC (Medical Assistance, Guidance, Instruction, and Correction), an egocentric medical activity dataset collected as part o

arXiv:2604.22189v1 Announce Type: new Abstract: This letter presents an energy-efficient multi-robot coverage path planning (MRCPP) framework for large, nonconvex Regions of Interest (ROI) containing

arXiv:2604.22595v1 Announce Type: new Abstract: CLIP has demonstrated strong generalization in visual domains through natural language supervision, even for video action recognition. However, most exi

arXiv:2604.22251v1 Announce Type: new Abstract: Variable impedance model predictive control (MPC) formulations that treat joint stiffness as an instantaneous decision variable operate on a feasible se

arXiv:2604.22328v1 Announce Type: cross Abstract: Driven by the transition towards a climate-neutral energy system, accurate energy time series forecasting is critical for planning and operation. Yet,

arXiv:2604.22334v1 Announce Type: new Abstract: Recent advances in pretraining 3D point cloud encoders (e.g., Point-BERT, Point-MAE) have produced powerful models, whose abilities are typically evalua

@FireworksAI_HQ deeply believes in delivering the frontier quality. We will spend all the effort giving our users and the broad community the best OSS model quality. Deepseek V4 API up anytime now aft

arXiv:2604.22093v1 Announce Type: new Abstract: Reliable visual perception under low illumination remains a core challenge for autonomous robotic systems, where degraded image quality directly comprom

On March 5, 2026, the much-anticipated paper for FlashAttention-4 (FA4) was published. The code was dropped on GitHub months ago; early benchmarks circulated, and preliminary results were presented at

arXiv:2604.22190v1 Announce Type: cross Abstract: CLIP-based person re-identification (ReID) methods aggregate spatial features into a single global exttt{[CLS]} token optimized for image-text alignme

arXiv:2601.11020v3 Announce Type: replace Abstract: Advances in mechanistic interpretability have identified special attention heads, known as retrieval heads, that are responsible for retrieving info

arXiv:2604.22601v1 Announce Type: cross Abstract: Large Language Models (LLMs) show promise in automated software engineering, yet their guarantee of correctness is frequently undermined by erroneous

Gemma 4 (26B + 31B) from @GoogleDeepMind is now available on the Fireworks Training Platform across the Managed and Training API workflows. Try SFT and DPO with smart defaults or your own custom loss

going to buy 2 rtx 6000 just because of the capabilities of local models becoming great! no more outsourcing of research to the api Xiaomi MiMo-V2.5 is now officially open-sourced！ MIT License, suppor

GPT-5.5 in Codex made a surprisingly solid table top RPG game masters guide & player guide, which it 'playtested.' It leans into the storytelling aspect, and still has some very LLM-y elements, but it

arXiv:2503.21435v3 Announce Type: replace Abstract: Recent advances in Vision-Language Models (VLMs) have shown promising capabilities in interpreting visualized graph data, offering a new perspective

Nous Research announced that their Hermes Agent repository has surpassed Anthropic's Claude Code repository in popularity metrics, likely referring to GitHub stars or similar engagement measures. This

🎁 Here's a new limited-time top-up reward. Grab bonus vouchers and keep exploring Kimi K2.6. 🔹20% bonus for 100 – 299 🔹25% bonus for 300 – 999 🔹30% bonus for $1,000+ Ends May 3. 🔗Details:https://platf

arXiv:2604.22482v1 Announce Type: new Abstract: While feed-forward 3D reconstruction models have advanced rapidly, they still exhibit degraded performance on panoramas due to spherical distortions. Mo

arXiv:2604.22750v1 Announce Type: new Abstract: The wide adoption of AI agents in complex human workflows is driving rapid growth in LLM token consumption. When agents are deployed on tasks that requi

arXiv:2511.18903v2 Announce Type: replace-cross Abstract: Due to the scarcity of high-quality data, large language models (LLMs) are often trained on mixtures of data with varying quality levels, even

arXiv:2604.22271v1 Announce Type: new Abstract: Large language models can detect their own errors and sometimes correct them without external feedback, but the underlying mechanisms remain unknown. We

In this post, we share how we applied Amazon Bedrock and the Amazon Nova family of models to reimagine our Title Suggestion feature. By combining metadata, computer vision, and retrieval-augmented gen

DeepSeek V4 models on Ollama Cloud support three thinking modes: 'No thinking' for fast answers, 'Thinking' for careful analysis, and 'Max thinking' for maximum reasoning effort . Users can adjust thi

https://x.com/ollama/status/2047598971435290992?s=20 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:clo

arXiv:2604.22442v1 Announce Type: new Abstract: We introduce HubRouter, a pluggable module that replaces O(n^2) attention layers with O(nM) hub-mediated routing, where M =20 shows increasing seed sens

If a major car company had AI fan boys and released a car with loose lug nuts and the wheels came off, after hyping it as the greatest thing ever, and a bunch of people died, those fan boys would say

arXiv:2507.03014v2 Announce Type: replace-cross Abstract: Large language models (LLMs) face significant copyright and intellectual property challenges as the cost of training increases and model reuse

Introducing our new work: “Learning to Orchestrate Agents in Natural Language with the Conductor” accepted at #ICLR2026 https://arxiv.org/abs/2512.04388 What if we trained an AI not to solve problems

Kimi K2.6 has achieved the top ranking on OpenRouter's weekly LLM leaderboard, marking a significant achievement for the model. The announcement expresses gratitude to developers using Kimi and indica

arXiv:2604.22302v1 Announce Type: new Abstract: Recent text-to-image (T2I) models have demonstrated impressive capabilities in photorealistic synthesis and instruction following. However, their reliab

arXiv:2508.05633v2 Announce Type: replace-cross Abstract: Live streaming platforms have become a dominant form of online content consumption, offering dynamically evolving content, real-time interacti

arXiv:2505.14990v3 Announce Type: replace Abstract: Often, multilingual language models are trained with the objective to map semantically similar content (in different languages) in the same latent s