Search: “model-releases”

SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing Alignment

arXiv:2606.25821v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) architectures have emerged as an increasingly influential paradigm as they offer a strategic balance between parameter s

Model Releases

Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis

DGX agent

arXiv:2606.25369v1 Announce Type: cross Abstract: While large language model (LLM)-based text-to-speech (TTS) systems have achieved high-quality speech synthesis, most existing systems focus on Englis

model-releasesarxiv-cs-cl

25 Jun 2026

SciRisk-Bench: A Risk-Dimension-Aware Benchmark for AI4Science Safety

arXiv:2606.18936v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly embedded in AI for Science (AI4Science) workflows, from scientific question answering and literature a

SFL-MTSC: Leveraging Semantic Frame-Level Multi-Task Self-Consistency for Robust Multi-Intent Spoken Language Understanding

arXiv:2606.25552v1 Announce Type: new Abstract: Prompt-based spoken language understanding (SLU) with large language models (LLMs) often suffers from inconsistent intent--slot structures due to decodi

Shapley-Inspired Feature Weighting in k-means with No Additional Hyperparameters

arXiv:2508.07952v2 Announce Type: replace Abstract: Clustering algorithms often assume all features contribute equally to the data structure, an assumption that usually fails in high-dimensional or no

ShutterMuse: Capture-Time Photography Guidance with MLLMs

arXiv:2606.25763v1 Announce Type: new Abstract: Real-world photography requires capture-time guidance for both camera framing and subject pose. Yet existing aesthetic cropping benchmarks mainly evalua

Silent Failures in Physics-Informed Neural Networks: Parameter Poisoning and the Limits of Loss-Based Validation

arXiv:2606.25151v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) embed governing equations in their loss function, enabling mesh-free solutions to partial differential equation

Small edits, large models: How Wikipedia advocacy shapes LLM values

arXiv:2606.24890v1 Announce Type: new Abstract: Can a small group of volunteers shape how AI systems discuss animal welfare, just by editing Wikipedia? We show that they can. Wikipedia appears in near

Small Initialization Matters for Large Language Models

arXiv:2606.17945v2 Announce Type: replace Abstract: Large language models provide a tractable system for asking how intelligence itself emerges, rather than only how LLMs can be engineered. Although p

SpaceX rocket launches in 2026 are insanely brutal SpaceX: • 76 operational launches ➝ 76 successes ➝ 0 failures The entire rest of the worl…

model-releaseselon-musk--x

SpaceX rocket launches in 2026 are insanely brutal SpaceX: • 76 operational launches ➝ 76 successes ➝ 0 failures The entire rest of the world combined: • 55 tracked launches ➝ 49 successes ➝ 6 failure

SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs

arXiv:2602.06566v3 Announce Type: replace-cross Abstract: Despite recent successes, test-time scaling -- i.e., dynamically expanding the token budget during inference as needed -- remains brittle for

Spatio-Temporal Mixture-of-Modality-Experts Diffusion for Quantitative DCE-MRI Synthesis from Incomplete MR Sequences

arXiv:2606.25535v1 Announce Type: new Abstract: Quantitative maps from dynamic contrast-enhanced MRI (DCE-MRI) are essential for tumor assessment but are often unavailable due to contrast-agent risks

Speech Codec Probing from Semantic and Phonetic Perspectives

arXiv:2603.10371v2 Announce Type: replace-cross Abstract: Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems. Speech tokenizers are expected to

SpeechEQ: Benchmarking Emotional Intelligence Quotient in Socially Aware Voice Conversational Models

arXiv:2606.25990v1 Announce Type: new Abstract: As multimodal conversational systems increasingly engage in spoken interaction, their ability to navigate paralinguistic social cues has become a critic

Spotlighting Task-Relevant Features: Object-Centric Representations for Better Generalization in Robotic Manipulation

arXiv:2601.21416v2 Announce Type: replace Abstract: The generalization capabilities of robotic manipulation policies are heavily influenced by the choice of visual representations. Existing approaches

SSMNBench: Diagnosing Image-based Cross-View Human-Object Understanding via Single-View Sufficiency and Multi-View Necessity

arXiv:2606.25634v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have shown remarkable progress in single-image perception, yet their ability to reason about complex cross-view

Stable-Shift: Biologically Structured Prediction of Transcriptional Responses to Unseen Gene Perturbations

arXiv:2606.24940v1 Announce Type: cross Abstract: Predicting transcriptional responses to genetic perturbations could reduce the experimental burden of functional genomics, but extrapolation to genes

Stage-Aware and Roughness-Constrained Diffusion Policy for Multi-Stage Robotic Polishing

arXiv:2606.25754v1 Announce Type: new Abstract: Polishing is a critical finishing process in high-end manufacturing fields such as aerospace, where surface quality directly affects the service perform

Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agents

arXiv:2606.25632v1 Announce Type: new Abstract: Recent LLM role-playing systems build character agents from novels by extracting characters, scenes, and relations. Yet long-narrative role-playing suff

STEB: A Speech-to-Speech Translation Expressiveness Benchmark for Evaluating Beyond Translation Fidelity

arXiv:2606.25529v1 Announce Type: cross Abstract: Speech-to-speech translation (S2ST) should preserve not only lexical meaning, but also expressive attributes: emotion, scenario style (e.g., news repo

Steering Vision-Language Models with Joint Sparse Autoencoders

arXiv:2606.25657v1 Announce Type: new Abstract: Sparse Autoencoders (SAEs) have shown promise for analyzing language models, but applying them to vision-language models (VLMs) often yields representat

Story Operators: Decomposing the Original o Sequel Transformation in Embedding Space

arXiv:2606.25379v1 Announce Type: new Abstract: I treat a book as a point in a sentence-embedding space and a literary transformation as an operation on points. Given an original novel and its sequel,

SurgAtlas: A Large-Scale Surgical Video-Language Dataset with 2,391 Hours of Open and Minimally Invasive Surgery

arXiv:2606.25905v1 Announce Type: new Abstract: We introduce SurgAtlas, the largest surgical video-language dataset to date, comprising 15,291 videos (2,391 hours) spanning 18 surgical specialties and

Swazure: Swarm Measurement of Pose for Flying Light Specks

arXiv:2606.25222v1 Announce Type: new Abstract: One may construct a 3D multimedia display using miniature drones configured with light sources, Flying Light Specks (FLSs). Swarms of FLSs localize to i

SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical Reasoning

arXiv:2507.16518v3 Announce Type: replace-cross Abstract: Recent advances in multimodal large language models (MLLMs) have shown impressive reasoning capabilities. However, further enhancing existing

TACO: Towards Task-Consistent Open-Vocabulary Adaptation in Video Recognition

arXiv:2606.25478v1 Announce Type: new Abstract: Adapting CLIP for open-vocabulary video recognition necessitates a delicate balance between newly acquired video knowledge and the pretrained generaliza

TacVerse: A Multi-Sensor Dataset and Benchmark for Cross-Sensor Vision-Based Tactile Perception

arXiv:2606.25877v1 Announce Type: new Abstract: Vision-based tactile sensors (VBTSs) enable robots to infer contact geometry and force-related cues by imaging deformation through an internal camera, y

Tensorion: A Tensor-Aware Generalization of the Muon Optimizer

arXiv:2606.25975v1 Announce Type: cross Abstract: Common first-order optimizers, such as Adam, implicitly treat each parameter block as an unstructured vector, which disregards the multilinear weight

The 4/elta Bound: Designing Predictable LLM-Verifier Systems for Formal Method Guarantee

arXiv:2512.02080v3 Announce Type: replace-cross Abstract: The integration of Formal Verification tools with Large Language Models (LLMs) offers a path to scale software verification beyond manual work

The underrated part of this announcement is that Fireworks has been quietly great behind the scenes helping us eval and serve these models B…

model-releasesfireworks-ai--x

The underrated part of this announcement is that Fireworks has been quietly great behind the scenes helping us eval and serve these models Big kudos to the Fireworks team! Kimi K2.7 Code and GLM 5.2 a

this video was also edited by Claude :)

This post from Thariq on X references a video that was edited using Claude, an AI assistant, likely highlighting Claude's capabilities in video editing or content creation workflows. Without access to

model-releasesthariq--x

Three Buddhist Vocabularies: Computational Stylometry of the English Pali Canon across Sutta, Vinaya, and Abhidhamma

arXiv:2606.25372v1 Announce Type: new Abstract: We present a computational stylometric analysis of the Tipitaka across all three Pitakas in English translation, extending earlier work on the Sutta Pit

TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems

arXiv:2606.25147v1 Announce Type: cross Abstract: User modeling in industrial recommender systems typically produces dense embeddings, which suffer from representational constraints inherent to fixed-

TopoCast: A Topological Fidelity Framework for Evaluating Transformer-Based Time Series Forecasting

arXiv:2606.25439v1 Announce Type: new Abstract: Deep learning-based models have achieved state-of-the-art performance in Time Series Forecasting (TSF), yet their evaluation remains dominated by pointw

Toten: A Knowledge-Based System For Structure-Preserving Representation Of Physical Quantities And Technical Notation In Brazilian Portuguese

arXiv:2606.19626v2 Announce Type: replace-cross Abstract: AI pipelines that reason quantitatively over technical text depend on input where physical quantities, numbers, units, and symbolic expression

Toward Low-Latency Vision-Language Models with Doubly-Correct Predictions in Egocentric Visual Understanding

arXiv:2606.25160v1 Announce Type: cross Abstract: The rapid rise of Vision-Language Models (VLMs) in egocentric visual understanding has made low-latency inference in human-robot collaborative (HRC) t

Training for the Model You Return: Improving Optimization for Iterate-Averaged Language Models

arXiv:2606.25086v1 Announce Type: new Abstract: Many modern Language Model (LM) pipelines return an averaged model, such as an exponential moving average of the training iterates, rather than the fina

TriViewBench: Controlled Complexity Scaling for Multi-View Structural Reasoning in MLLMs

arXiv:2606.26029v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) demonstrate strong performance on standard visual question answering benchmarks, yet their scalability under co

Two-dimensional Hyperbolic RNN Neural Quantum State

arXiv:2606.25600v1 Announce Type: cross Abstract: In the first part of this work, we construct the first type of two-dimensional (2D) hyperbolic neural quantum state (NQS) in the form of the Lorentz 2

Type Checking Project Haystack Grids using JSON Schema and Pydantic

arXiv:2606.24891v1 Announce Type: cross Abstract: Ontologies enable scalable energy services in buildings by supporting interoperability and automation. Project Haystack is a building ontology that is

Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasets

arXiv:2606.25760v1 Announce Type: cross Abstract: Computer-use agents turn vision-language model (VLM) predictions into executable GUI clicks, so reliable uncertainty estimates are essential for rejec

USS: Unified Spatial-Semantic Prompts for Embodied Visual Tracking with Latent Dynamics Learning

arXiv:2606.25880v1 Announce Type: new Abstract: Embodied Visual Tracking (EVT) requires an agent to continuously follow a specified target while actively moving through dynamic environments. However,

V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning

arXiv:2606.25319v1 Announce Type: new Abstract: Fine-grained visual reasoning requires multimodal large language models (MLLMs) to identify task-relevant visual evidence and ground their reasoning in

Verifiable Manifest Signing and Transparency Enforcement for Secure MCP-Based LLM Pipelines

arXiv:2601.23132v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed in tool-driven environments such as healthcare analytics, financial systems, retrieval-

Video models are hard. Real-time video models are even harder. Loved this breakdown by @itunpredictable on how we productionized Runway Char…

model-releasescristobal-valenzuela--x

Video models are hard. Real-time video models are even harder. Loved this breakdown by @itunpredictable on how we productionized Runway Characters, our real-time interactive avatar model. We had to fi

VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks

arXiv:2606.25592v1 Announce Type: new Abstract: Recent advancements in Image-to-Video (I2V) generation have transformed input images from simple appearance references into interactive control interfac

We built LiteParse, the fastest document parsing solution on the planet and made it open source. And it just hit 10k github stars. 🦙 Fast t…

model-releasesjerry-liu--x

We built LiteParse, the fastest document parsing solution on the planet and made it open source. And it just hit 10k github stars. 🦙 Fast to run. Fast to love. Thanks for building with us. If you have

What Actually Works for Spacecraft Fault-Tolerant Control: An Honest Settled-Gate Benchmark of Learned and Classical Methods

arXiv:2606.25374v1 Announce Type: new Abstract: Recent learned fault-tolerant-control (FTC) work reports high success on spacecraft actuator faults, but often in simulation, on narrow fault sets, and