model releases

Parsimonious disturbance-aware minimum-time planning with parametric uncertainty

model-releasesarxiv-cs-ro

arXiv:2607.13312v1 Announce Type: new Abstract: This study presents and validates a minimum-lap-time planning (MLTP) framework for motorsport applications that embeds robustness against both state dis

Model Releases

Partially Correlated Verifier Cascades in LLM Harnesses: Concave Log-Odds, Polynomial Reliability, and Blind-Spot Ceilings

DGX agent

arXiv:2607.13918v1 Announce Type: cross Abstract: Serial verification gates are a core reliability primitive in LLM harnesses: a candidate answer is returned only if k verifier calls all accept it. Un

model-releasesarxiv-cs-ai

16 Jul 2026

Peak-End-Net: A Peak-End Rule Inspired Framework for Generalizable Video Aesthetic Assessment

arXiv:2607.13941v1 Announce Type: new Abstract: Video aesthetic assessment (VAA) aims to predict how aesthetically pleasing a video is, yet remains far less explored than other visual assessment tasks

PiVoT: A Variational Solution for Real-time Large-scale Multi-object Detection and Tracking under Heavy Clutter

arXiv:2607.13891v1 Announce Type: cross Abstract: Multi-object detection and tracking from noisy point clouds remain challenging in many data-scarce radar applications. Current Bayesian trackers based

Policy of Thoughts: Scaling Test-Time Training for LLM Reasoning via Online Policy Evolution

arXiv:2601.20379v2 Announce Type: replace Abstract: Large language models (LLMs) struggle with complex, long-horizon reasoning due to instability caused by their frozen policy assumption. Current test

PQFA: Parallel Quantum Feature Augmentation of Fused Representations for Multimodal Classification

arXiv:2607.13466v1 Announce Type: new Abstract: Most multimodal learning methods improve how heterogeneous representations are aligned and fused, while post-fusion enhancement remains less explored. W

Quantum Circuit Vision: Cost-Aware Evaluation of Visual AI Agents for Quantum Code Generation

arXiv:2607.10057v1 Announce Type: cross Abstract: Can AI agents visually comprehend quantum circuit diagrams and generate verified executable code--and at what cost? We present Quantum Circuit Vision,

Qwen3.5 122B-A10B · ROCmFP4 iMatrix

model-releasesr-localllama

Hola Strix and AMD stacker frendios. Read the Lineage and Credits, this uses charlie12345/ROCmFPX, won't work on native llama.cpp yet. 122B total · 10B active · 60.70 GiB · 28.50 tok/s MTP-off · BF16

RAGthoven at SemEval-2026 Task 1: A Multi-Stage Pipeline Walks Into a Benchmark and Barely Clears the Bar

arXiv:2607.13189v1 Announce Type: cross Abstract: We present RAGthoven, our system for SemEval-2026 Task 1 (MWAHAHA), Subtask A (multilingual constrained humor generation in English, Spanish, and Chin

Representation-Based Exploration for Language Models: From Test-Time to Post-Training

arXiv:2510.11686v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) promises to expand the capabilities of language models, but it is unclear if current RL techniques promote the dis

RF Spectrogram Anomaly Detection with Quantum Kitchen Sinks: Architecture, Representation, and Hardware Validation

arXiv:2607.13897v1 Announce Type: new Abstract: The broadcast nature of wireless channels exposes radio-frequency (RF) networks to anomalous and malicious transmissions, making anomaly detection a fun

S-squared-VLA: Decoupling Semantic and Spatial Streams in Vision-Language-Action Models for Autonomous Driving

model-releasesarxiv-cs-ro

arXiv:2607.13926v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have demonstrated remarkable potential for high-level reasoning in autonomous driving, yet they fundamentally struggle to

Safe Overtaking for Autonomous Racing Using Hierarchical Optimization and Learning-Based Control

model-releasesarxiv-cs-ro

arXiv:2607.13348v1 Announce Type: new Abstract: Autonomous racing overtaking requires balancing competitive performance with safety under nonlinear vehicle dynamics and real-time constraints. Model Pr

Safeguard-Conditioned Uplift: Measuring Utility-Risk Frontiers for Dual-Use Biology Assistants

arXiv:2607.13039v1 Announce Type: cross Abstract: Safety evaluations for dual-use biology assistants often measure base-model capability, refusal behavior, or jailbreak success. These metrics miss a d

ScanFocus: A Coarse-to-Fine Framework for Spatio-Temporal Video Grounding

arXiv:2607.13421v1 Announce Type: cross Abstract: Spatio-Temporal Video Grounding (STVG) aims to retrieve the visual trajectory of a specific object from a video stream as described by a natural langu

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge

arXiv:2607.13088v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly moving from research settings into the wild, deployed on enterprise infrastructure, personal devices, and edg

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training?

arXiv:2607.13192v1 Announce Type: new Abstract: Self-supervision is a powerful technique for learning visual representations from unlabeled data. Existing techniques primarily adopt a two-stage approa

Set-shifting Behavioral Test for Harnessed Agents

arXiv:2607.13396v1 Announce Type: new Abstract: What happens to an LLM agent's tool choice when the reliable tool silently changes within an ongoing session? We borrow set-shifting from cognitive psyc

SingGuard-NSFA: Extensible Guardrails for Agentic AI via Generative Reasoning and Real-Time Classification

arXiv:2607.13081v1 Announce Type: cross Abstract: We present nsfaguard, a guardrail framework for securing agentic AI systems against operational threats, such as prompt injection, sensitive informati

SPINE: Bridging the Cyber-Physical Gap with Agentic AI

arXiv:2607.13049v1 Announce Type: new Abstract: Foundation models have given robots a sophisticated brain for complex decision-making, yet deploying that intelligence into a physical platform still de

STOCKTAKE: Measuring the Gap Between Perception and Action in LLM Agents with a Fair Oracle

arXiv:2607.13618v1 Announce Type: new Abstract: LLM agents are increasingly evaluated on multi-week decision tasks in which the state that drives cost is never directly observed. On such tasks the fin

Symbiosis-Inspired Knowledge Distillation for Incremental Object Detection

arXiv:2607.13452v1 Announce Type: cross Abstract: Incremental object detection (IOD) aims to extend detectors to new categories while retaining previously acquired knowledge. Existing methods often ad

Targeted Recovery of Weight-Space Mechanisms From Neural Networks

arXiv:2607.13047v1 Announce Type: new Abstract: Parameter decomposition (PD) decomposes neural networks into interpretable computational components that faithfully reflect the original network's opera

The Dynamic Verifiable Multi-Agent Human Agentic Loyalty Loop (DVM-HALL) Model and the Net Human-Agent Score (NHAS) in Autonomous Commerce

arXiv:2607.13998v1 Announce Type: cross Abstract: The rapid proliferation of Agentic Artificial Intelligence fundamentally disrupts traditional customer loyalty paradigms. As AI evolves from passive r

The Perplexity Trap: When Patent Law Makes Human Writing Look Like AI

arXiv:2607.13044v1 Announce Type: cross Abstract: The European Patent Office (EPO) reported record filings in 2025, and the 2026 EPO Guidelines hold applicants strictly responsible for LLM-assisted co

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't

arXiv:2607.13346v1 Announce Type: cross Abstract: Alignment faking is dangerous because a model can appear compliant under monitoring while preserving behavior it would reveal when unmonitored. When n

Thresholded Cross-Attention for Reliable Intensity-Chromaticity Fusion in Low-Light Image Enhancement

arXiv:2607.13925v1 Announce Type: new Abstract: Low-Light Image Enhancement (LLIE) requires a careful balance among noise suppression, color fidelity, and efficiency. Recent HVI-based methods alleviat

Towards Spatial Supersensing in the Wild

arXiv:2607.13681v1 Announce Type: new Abstract: Humans can efficiently parse continuous sensory streams, from hours to years, scaffolding an internal world model that grounds spatial reasoning and pre

TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents

arXiv:2607.13988v1 Announce Type: new Abstract: Multi-turn agents solve complex tasks through extended sequences of tool interactions before producing a final answer, making credit assignment a fundam

Traffic-Aware Randomized Smoothing for LLM-Based Network Intrusion Detection

arXiv:2607.13801v1 Announce Type: cross Abstract: Large language model (LLM)-based intrusion detection systems (IDS) are increasingly studied for security monitoring, yet their robustness against feas

Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth

arXiv:2607.14018v1 Announce Type: cross Abstract: We investigate how each component of the Transformer feedforward block architecture design determines how much rank survives across depth at initializ

UESF-Bench: Benchmarking and Probing for Unified Embodied Seeking and Following

arXiv:2607.13621v1 Announce Type: new Abstract: Language-guided human following is an important capability for embodied agents, but existing benchmarks typically assume that the target person is visib

UniPhysGen: Unified Physical Grounding for Simulation-Ready 3D Assets

arXiv:2607.13586v1 Announce Type: new Abstract: Physically grounded 3D assets are increasingly important for embodied AI and robotic simulation. However, most existing 3D assets lack unified physical

Unsupervised Detection of Entry and Exit Regions from Vehicle Trajectories for Camera-Agnostic Turning Movement Counts

arXiv:2607.10949v2 Announce Type: replace Abstract: Turning movement counts are essential for intersection-level traffic management, yet their collection remains predominantly manual due to the cost o

v0.32.1

model-releasesollama-releases

What's Changed Improved Gemma 4 tool calling and multi-turn reasoning, including more reliable tool-response continuations Fixed a recurrent MLX model cache leak that could increase memory use across

Value Drifts: Tracing Value Alignment During LLM Post-Training

arXiv:2510.26707v2 Announce Type: replace-cross Abstract: As LLMs occupy an increasingly important role in society, they are more and more confronted with questions that require them not only to draw

VGIF-Score: Interpretable and Diagnostic Evaluation of Spatio-Temporal Instruction Following in Video Generation

arXiv:2607.13527v1 Announce Type: new Abstract: Recent video generation models (VGMs) have made substantial progress in visual fidelity, yet their ability to follow long, compositional instructions re

VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders

arXiv:2607.14088v1 Announce Type: new Abstract: Video generative models commonly rely on latent spaces learned by 3D Variational Autoencoders (3D-VAEs). However, conventional 3D-VAEs are mainly optimi

WaterMoE: Expert-Routing-based Watermarking for High Fidelity and Efficiency

arXiv:2607.13099v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable success but raise growing concerns about content provenance and misuse, motivating the need for

Weight Feedback Computes the Jacobian Transpose Locally in Modern Deep Networks

arXiv:2607.13380v1 Announce Type: new Abstract: Predictive Coding (PC) offers a biologically motivated alternative to backpropagation via local weight updates, yet routing error between layers still r

We’re excited to collaborate with NVIDIA to build the next generation of Fugu orchestration models together, by incorporating leading open-w…

model-releasesdavid-ha--x

We’re excited to collaborate with NVIDIA to build the next generation of Fugu orchestration models together, by incorporating leading open-weights models. Sakana AI Teams With NVIDIA to Advance Open M

When Agents Disagree With Themselves: Behavioral Consistency as an Uncertainty Signal for LLM Agents

arXiv:2602.11619v2 Announce Type: replace Abstract: Running the same LLM agent on identical inputs yields 2.3-4.2 distinct action sequences per 10 runs; this behavioral variance constitutes a training

When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs

arXiv:2602.17659v2 Announce Type: replace Abstract: Vision-Language-Action models (VLAs) promise to ground language instructions in robot control, yet in practice often fail to faithfully follow langu

1D-Bench: A Benchmark for Iterative UI Code Generation with Visual Feedback in Real-World

arXiv:2602.18548v2 Announce Type: replace-cross Abstract: Design-to-code translates high-fidelity UI designs into executable front-end implementations, but progress remains hard to compare due to inco

🥉 3rd place: CashFromChaos, by David Diaz (@davddiazm) CashFromChaos starts from a single seller input and automates everything up until a …

model-releasesnous-research--x

🥉 3rd place: CashFromChaos, by David Diaz (@davddiazm) CashFromChaos starts from a single seller input and automates everything up until a completed sale. You send a photo and a one-line clue, and Her

A Calibrated Multimodal Ensemble for Ambivalence/Hesitancy Recognition: System Description and Private-Test Submission Strategy

arXiv:2607.12176v1 Announce Type: new Abstract: Ambivalence and hesitancy (A/H) undermine digital behaviour-change interventions, and recognizing them automatically from video is the goal of the ABAW

A closer look at improved intelligence in GPT-Live: the model can keep a conversation going while helping with multiple tasks at once, like …

A closer look at improved intelligence in GPT-Live: the model can keep a conversation going while helping with multiple tasks at once, like checking flights, pulling up local weather, and shaping an i

model-releasesopenai--x

A Comparative Analysis of Institutional and Course Generative AI Policies within Higher Education: Implications for Instruction in Computing Education

arXiv:2607.12296v1 Announce Type: cross Abstract: With the increased use of generative AI (GenAI) applications such as ChatGPT, higher education institutions (HEIs) have released a range of guidelines