Search: “model-releases”

Rethinking Federated Graph Foundation Models: A Graph-Language Alignment-based Approach

arXiv:2601.21369v2 Announce Type: replace Abstract: Recent studies of federated graph foundational models (FedGFMs) break the idealized and untenable assumption of having centralized data storage to t

Model Releases

Reusing Rollouts under Policy Lag: Prefix-Normalized Policy Optimization for LLM Reinforcement Learning

DGX agent

arXiv:2608.01418v1 Announce Type: cross Abstract: Autoregressive rollout generation is a major computational cost in reinforcement learning for large language models. Reusing each rollout batch for ad

model-releasesarxiv-cs-lg

4 Aug 2026

Riemannian Attention Mechanisms for Transformers: A Theoretical Framework and Architecture Design

arXiv:2608.01283v1 Announce Type: new Abstract: All Transformer-based large language models compute attention via the Euclidean inner product, an architectural choice that Dong et al. (2021) proved ca

Right Answer, Wrong Method: Shortcut Hacking Misleads the Evaluation of LLM Reasoning on Frontier Science Benchmarks

arXiv:2608.02442v1 Announce Type: cross Abstract: Scientific reasoning benchmarks typically evaluate large language models (LLMs) using final-answer accuracy. However, a correct answer does not necess

RING: Retrieval-Internalized Generation for Continual Large-Scale Knowledge Injection

arXiv:2608.01630v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves factuality but adds latency and engineering overhead at serving time. We propose RING (Retrieval-Internali

RIT*: Riemannian Informed Trees for Cost-Adaptive Optimal Motion Planning

model-releasesarxiv-cs-ro

arXiv:2608.00822v1 Announce Type: new Abstract: We present Riemannian Informed Trees (RIT*), a planning framework that replaces Euclidean primitives in batch-informed search with their Riemannian coun

Robust Watermarks Meet Backdoored Models: Evading Diffusion Semantic Watermarks via Stealthy Backdoor

arXiv:2608.00543v1 Announce Type: cross Abstract: Although semantic watermarking is considered a promising safeguard for images generated by Latent Diffusion Models (LDMs), the reliance of the waterma

Role Steering of Language Models for Social Simulations

arXiv:2608.00023v1 Announce Type: new Abstract: Social simulations built from language-model agents need role-conditioned behavior that can be checked before agents are placed into a simulated populat

Round-Trip Consistency: Bidirectional Diffusion Models Can Predict Their Own Rollout Errors

arXiv:2608.00675v1 Announce Type: cross Abstract: Autoregressive models accumulate error over long rollouts, yet at deployment there is no ground truth to measure it against. We train a single conditi

Routing for long-horizon coding agents is a big deal. @notdiamond_ai just announced a model router that works natively with Claude Code. Thi…

Routing for long-horizon coding agents is a big deal. @notdiamond_ai just announced a model router that works natively with Claude Code. This is huge. It picks the model and reasoning effort before ea

model-releasesdair-ai--x

RSC-GestureNet: Reliability-Aware Selective Causal Recognition of Chinese Traffic Police Gestures

arXiv:2608.02200v1 Announce Type: new Abstract: Traffic police gestures are safety-critical perception cues for autonomous driving. A deployable recognizer must infer commands causally from continuous

RSRA: Training-Free Probing of Representation Sensitivity for Efficient LoRA Rank Allocation

arXiv:2607.09757v2 Announce Type: replace Abstract: Parameter-efficient fine-tuning enables large language models to adapt to downstream tasks with substantially lower computational and storage cost,

RSVideo: Are Your Vision-Language Models Ready for Remote Sensing Videos?

arXiv:2608.02039v1 Announce Type: new Abstract: Remote-sensing videos enable real-time observation of changes in target attributes, short-term activities, and scene evolution. They record motion, acti

Running fast is not enough, you need fast AND correct An excellent addition from @ArtificialAnlys to make sure that the flashy speed numbers…

model-releasesfireworks-ai--x

Running fast is not enough, you need fast AND correct An excellent addition from @ArtificialAnlys to make sure that the flashy speed numbers are backed by 100% matching accuracy Announcing the Artific

S^4R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching

arXiv:2608.00528v1 Announce Type: new Abstract: The growth of context window lengths in Large Language Models (LLMs) significantly enhances their long-context capabilities but incurs prohibitive memor

SAFE-Merge: Data-Free Continual Model Merging with General Knowledge Preservation

arXiv:2608.01184v1 Announce Type: new Abstract: Data-free continual model merging must incorporate a stream of specialized models while retaining both pretrained general knowledge and previously acqui

SafeBuild-Bench: A Temporal-Robust Construction Safety Benchmark with Graph-Enhanced Data Mining

arXiv:2608.00068v1 Announce Type: new Abstract: Construction-safety models must handle concrete deployment risks, such as a worker standing near a scaffold edge without guardrails, rather than only re

SCHEDBench: A Benchmark for Evaluating LLM Constraint Faithfulness in Natural-Language Combinatorial Scheduling

arXiv:2608.00991v1 Announce Type: cross Abstract: This paper introduces SCHEDBench, a natural-language benchmark for evaluating combinatorial scheduling constraint faithfulness under surface-form vari

SCOPE: Entanglement Frontier Escape for Source-Free Class Unlearning

arXiv:2608.02058v1 Announce Type: new Abstract: Source-free class unlearning erases whole classes using only the forget data, judged at the representation level, where features can leak a class the he

ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step

arXiv:2608.02358v1 Announce Type: new Abstract: To operate robustly in open-world environments, autonomous agents should be able to infer the behavior of unfamiliar systems through interaction alone,

Self-composing neural operators for high-frequency and multiscale PDE surrogates

arXiv:2508.20650v2 Announce Type: replace Abstract: Addressing the computational challenges of high-frequency and multiscale partial differential equations (PDEs), this work introduces a self-composin

Semantic-Guided Cross-Sensor Super Resolution of Remote Sensing Images: A Gated Dual Conditioning Flow Matching Model

arXiv:2510.23816v3 Announce Type: replace Abstract: High spatial resolution satellite imagery is critical for monitoring fine-scale Earth surface processes, but is often limited by cost and revisit ti

SERL-SQL: Selective Hindsight Distillation for Text-to-SQL Reinforcement Agentic Learning

arXiv:2608.00485v1 Announce Type: new Abstract: Recent Text-to-SQL systems increasingly rely on multi-turn interaction, execution feedback, and reinforcement learning. However, most existing methods u

Shieldstral is available under Apache 2.0. Try it: https://huggingface.co/mistralai/Shieldstral-1.0

model-releasesmistral-ai--x

**Shieldstral** is a 3‑billion‑parameter open‑weights model developed by Mistral AI for content safety. It can be deployed on-device and is distributed under the Apache 2.0 license. The model is avail

Similarity-Aware Machine Unlearning

arXiv:2608.00246v1 Announce Type: new Abstract: Machine unlearning removes the influence of user-specified training examples from a trained model, avoiding the need to retrain it from scratch. Localiz

Simulation-Based Plate-Reverb Parameter Estimation from a Single Impulse Response

arXiv:2608.00656v1 Announce Type: cross Abstract: We present a simulation-trained, non-iterative estimator for Task A of the 1st DAFx Parameter Estimation Challenge. Each unnormalized plate-reverb imp

SIPTraj: Map-Free End-to-End Trajectory Prediction via Physics-Guided Scene Interaction

model-releasesarxiv-cs-ro

arXiv:2608.00779v1 Announce Type: new Abstract: Trajectory prediction of surrounding agents is a prerequisite for safe planning and decision making in autonomous driving. Without high-definition (HD)

SLMs as Multi-Agent Routers: A Progressive SFT and Reinforcement Learning Approach

arXiv:2608.00030v1 Announce Type: new Abstract: Specialised retrieval agents typically surface higher quality results than general-purpose search, but selecting the optimal agent for a given query rem

SoM-1K: A Thousand-Problem Benchmark Dataset for Strength of Materials

arXiv:2509.21079v2 Announce Type: replace Abstract: Foundation models have shown remarkable capabilities in various domains, but their performance on complex, multimodal engineering problems remains l

SoniSpeech: A Large-Scale Open-Vocabulary Tri-Modal Dataset for Wearable Silent Speech Interfaces

arXiv:2608.00803v1 Announce Type: cross Abstract: Wearable silent speech interfaces (SSIs) are limited to small, closed vocabularies. Approaches achieving larger vocabularies require obtrusive hardwar

Sources and filings: Google assembled a ~200B financing program for Anthropic, with 150B+ tied to TPUs and involving Broadcom, Blackstone, Apollo, and others (Financial Times)

Financial Times: Sources and filings: Google assembled a ~200B financing program for Anthropic, with 150B+ tied to TPUs and involving Broadcom, Blackstone, Apollo, and others — Private credit, chip le

model-releasestechmeme

SPARC-Rad: A Multimodal Benchmark Dataset and Evaluation Pipeline for Spatial and Anatomical Reasoning in Radiology Vision-Language Models

arXiv:2608.00100v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly being evaluated for medical imaging, but many available benchmarks emphasize disease classification, repo

SPARE: Structural Parameter-Free Affinity Regularization for Flow Matching

arXiv:2608.01990v1 Announce Type: new Abstract: Denoising diffusion transformers achieve strong generation quality but converge slowly during training. Regularizing their internal representations has

SpatialQuery: Benchmarking Geometry-Grounded Multi-Instance Spatial Reasoning in Vision-Language Models

arXiv:2608.01709v1 Announce Type: new Abstract: Vision-language models (VLMs) achieve strong semantic understanding but remain unreliable in metric spatial reasoning, particularly when queries require

SpatioLM: Towards General Physical Spatial Intelligence in Vision-Language Models

arXiv:2608.01899v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) perform well on commonsense reasoning tasks but struggle with visual spatial reasoning. Most existing solutions introduc

SPECTRA: Band-Routed Embedding and Stage-Wise LoRA for Cross-Sensor Fine-Tuning of Geospatial Foundation Models

arXiv:2608.01751v1 Announce Type: new Abstract: Geospatial foundation models (GeoFMs), pretrained on large-scale geospatial data such as Earth observation (EO), climate, and weather data, have shown p

SphereVideo: Prototype-anchored Hyperspherical Boundary for Continual AI-generated Video Detection

arXiv:2608.01334v1 Announce Type: new Abstract: AI-generated video (AIGV) detection aims to distinguish real videos from AI-generated ones. In practice, detectors trained on existing data often fail t

ST-LoRA: Single Trajectory LoRA Ensemble for Uncertainty Aware Agricultural Segmentation

arXiv:2608.01530v1 Announce Type: new Abstract: Reliable decision-support in digital agriculture requires accurate predictions and well-calibrated uncertainty estimates, particularly for dense predict

Staged Multi-Agent Training (SMAT) for Hip Exoskeletons: Metabolic and Biomechanical Validation of a Simulation-Trained Co-Adaptive Controller

arXiv:2608.00715v1 Announce Type: cross Abstract: Learning-based controllers can deliver exoskeleton assistance after training entirely in physics-based simulation, yet few controllers that address hu

Structured Memory for Edge Language Models: Persistent Context and Corpus Retrieval via O(1) SSM State Injection

arXiv:2608.02560v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) imposes a prefill cost proportional to retrieved context length, and -- with Transformer backbones -- a KV-cache th

Structured Proxy Features for Multimodal NSCLC Survival Prediction from Pretreatment CT

arXiv:2608.00446v1 Announce Type: new Abstract: Lung cancer results in roughly 1.8 million fatalities annually worldwide, with non-small cell lung cancer (NSCLC) comprising the majority of cases. Desp

Style Wins, Substance Loses: A Diagnosis of LLM-as-Judge in Idea Generation

arXiv:2608.01666v1 Announce Type: new Abstract: However, whether these judges truly evaluate the scientific substance of ideas or are influenced by superficial stylistic presentation remains an open q

SVGEval: A Vision-Grounded Framework for Perceptual-Quality Benchmarking and Evaluation in Text-to-SVG Generation

arXiv:2608.01977v1 Announce Type: new Abstract: Multimodal large models are increasingly used to generate scalable vector graphics (SVG), but reliable evaluation remains underexplored. Existing protoc

sweet, i finally set up my chatgpt, codex, claude, & claude code to have a shared memory - so i can ask one of them what i've worked on rece…

model-releasesyohei-nakajima--x

sweet, i finally set up my chatgpt, codex, claude, & claude code to have a shared memory - so i can ask one of them what i've worked on recently across all four of them for codex/cc, i'm using local h

SyncPlan: Long-Horizon LLM Coordination with Explicit Synchronization and Adaptive Correction

model-releasesarxiv-cs-ro

arXiv:2608.01652v1 Announce Type: new Abstract: LLM-based multi-agent coordination faces a fundamental trade-off between efficiency and adaptivity in dynamic environments. Existing approaches typicall

T^2exture: Sparsely Perturbed Thermal-to-Texture Imaging

arXiv:2608.02192v1 Announce Type: new Abstract: Thermal imaging remains effective under adverse illumination, yet passive long-wave infrared (LWIR) measurements often lack fine texture. Existing therm

TAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured Generation

arXiv:2603.00025v3 Announce Type: replace Abstract: Direct Preference Optimization (DPO) is effective for offline alignment but poorly matched to ontology-driven structured prediction, where preferred

TabDPT-Turbo: Efficient In-Context Learning for Tabular Prediction

arXiv:2608.01400v1 Announce Type: new Abstract: Tabular foundation models, driven by in-context learning, have rapidly grown in quality and popularity. However, recent approaches with either cell-base