model releases

ArchSym: Detecting 3D-Grounded Architectural Symmetries in the Wild

arXiv:2604.22202v1 Announce Type: new Abstract: Symmetry detection is a fundamental problem in computer vision, and symmetries serve as powerful priors for downstream tasks. However, existing learning

Model Releases

ArmSSL: Adversarial Robust Black-Box Watermarking for Self-Supervised Learning Pre-trained Encoders

DGX agent

arXiv:2604.22550v1 Announce Type: cross Abstract: Self-supervised learning (SSL) encoders are invaluable intellectual property (IP). However, no existing SSL watermarking for IP protection can concurr

model-releasesarxiv-cs-ai

27 Apr 2026

AromaGen: Interactive Generation of Rich Olfactory Experiences with Multimodal Language Models

arXiv:2604.01650v2 Announce Type: replace-cross Abstract: Smell's deep connection with food, memory, and social experience has long motivated researchers to bring olfaction into interactive systems. Y

Asymmetric Goal Drift in Coding Agents Under Value Conflict

arXiv:2603.03456v2 Announce Type: replace Abstract: Coding agents are increasingly deployed autonomously, at scale, and over long-context horizons. To be effective and safe, these agents must navigate

Atlas-Alignment: Making Interpretability Transferable Across Language Models

arXiv:2510.27413v2 Announce Type: replace-cross Abstract: Interpretability is crucial for building safe, reliable, and controllable language models, yet existing interpretability pipelines remain cost

ATRS: Adaptive Trajectory Re-splitting via a Shared Neural Policy for Parallel Optimization

model-releasesarxiv-cs-ro

arXiv:2604.22715v1 Announce Type: new Abstract: Parallel trajectory optimization via the Alternating Direction Method of Multipliers (ADMM) has emerged as a scalable approach to long-horizon motion pl

Bridging the Long-Tail Gap: Robust Retrieval-Augmented Relation Completion via Multi-Stage Paraphrase Infusion

arXiv:2604.22261v1 Announce Type: new Abstract: Large language models (LLMs) struggle with relation completion (RC), both with and without retrieval-augmented generation (RAG), particularly when the r

Calibrating Behavioral Parameters with Large Language Models

arXiv:2602.01022v2 Announce Type: replace-cross Abstract: Behavioral parameters such as loss aversion, herding, and extrapolation are central to asset pricing models but remain difficult to measure re

Call-Chain-Aware LLM-Based Test Generation for Java Projects

arXiv:2604.22046v1 Announce Type: cross Abstract: Large language models (LLMs) have recently shown strong potential for generating project-level unit tests. However, existing state-of-the-art approach

Can Large Language Models Adequately Perform Symbolic Reasoning Over Time Series?

arXiv:2508.03963v4 Announce Type: replace Abstract: Uncovering hidden symbolic laws from time series data, as an aspiration dating back to Kepler's discovery of planetary motion, remains a core challe

Categorical Perception in Large Language Model Hidden States: Structural Warping at Digit-Count Boundaries

arXiv:2603.28258v2 Announce Type: replace-cross Abstract: Categorical perception (CP) -- enhanced discriminability at category boundaries -- is among the most studied phenomena in perceptual psycholog

ChangeQuery: Advancing Remote Sensing Change Analysis for Natural and Human-Induced Disasters from Visual Detection to Semantic Understanding

arXiv:2604.22333v1 Announce Type: cross Abstract: Rapid situational awareness is critical in post-disaster response. While remote sensing damage assessment is evolving from pixel-level change detectio

CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution

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

CLARITY: A Framework and Benchmark for Conversational Language Ambiguity and Unanswerability in Interactive NL2SQL Systems

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

CNSL-bench: Benchmarking the Sign Language Understanding Capabilities of MLLMs on Chinese National Sign Language

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

Contexts are Never Long Enough: Structured Reasoning for Scalable Question Answering over Long Document Sets

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

Decoding High-Dimensional Finger Motion from EMG Using Riemannian Features and RNNs

model-releasesarxiv-cs-lg

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

Deep Learning for Model Calibration in Simulation of Itaconic Acid Production

model-releasesarxiv-cs-lg

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 / 3.4…

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 Her…

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

model-releasesollama--x

Dharma, Data and Deception: An LLM-Powered Rhetorical Analysis of Cow-Urine Health Claims on YouTube

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

Different Strokes for Different Folks: Writer Identification for Historical Arabic Manuscripts

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

DimABSA: Building Multilingual and Multidomain Datasets for Dimensional Aspect-Based Sentiment Analysis

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

Distance-Misaligned Training in Graph Transformers and Adaptive Graph-Aware Control

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, …

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

EgoMAGIC- An Egocentric Video Field Medicine Dataset for Training Perception Algorithms

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

Energy-Efficient Multi-Robot Coverage Path Planning of Non-Convex Regions of Interests

model-releasesarxiv-cs-ro

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

EV-CLIP: Efficient Visual Prompt Adaptation for CLIP in Few-shot Action Recognition under Visual Challenges

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

False Feasibility in Variable Impedance MPC for Legged Locomotion

model-releasesarxiv-cs-ro

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

FETS Benchmark: Foundation Models Outperform Dataset-specific Machine Learning in Energy Time Series Forecasting

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,

FILTR: Extracting Topological Features from Pretrained 3D Models

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 th…

@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

FLARE-BO: Fused Luminance and Adaptive Retinex Enhancement via Bayesian Optimisation for Low-Light Robotic Vision

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

FlashAttention-4 gives the NVIDIA Blackwell platform its most optimized attention kernel yet

model-releaseslambda-labs

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

From Global to Local: Rethinking CLIP Feature Aggregation for Person Re-Identification

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

From Interpretability to Performance: Optimizing Retrieval Heads for Long-Context Language Models

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

From Natural Language to Verified Code: Toward AI Assisted Problem-to-Code Generation with Dafny-Based Formal Verification

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. …

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

model-releasesclem-delangue--x

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 storyte…

model-releasesethan-mollick--x

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

Graph-to-Vision: Multi-graph Understanding and Reasoning using Vision-Language Models

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

Happy to announce that Hermes Agent's repo just surpassed Anthropic's Claude Code repo

model-releasesnous-research--x

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 $3…

model-releaseskimi-moonshot--x

🎁 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

Holo360D: A Large-Scale Real-World Dataset with Continuous Trajectories for Advancing Panoramic 3D Reconstruction and Beyond

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

How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks

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

How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining

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

How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals

model-releasesarxiv-cs-lg

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

How Popsa used Amazon Nova to inspire customers with personalised title suggestions

model-releasesaws-ml-blog

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