model releases

RecoverFly: A Failure-Aware Reinforcement Learning Post-Training Framework for Aerial Vision-Language Navigation

arXiv:2608.09467v1 Announce Type: cross Abstract: Unmanned aerial vehicle vision-language navigation (UAV-VLN) requires agents to translate visual observations and language instructions into reliable

Model Releases

Reducing Pretraining-Generation Mismatch in Diffusion Language Models

DGX agent

arXiv:2608.09424v1 Announce Type: new Abstract: Autoregressive language models align training and use: generation conditions on a clean prompt, and training predicts future tokens from clean left cont

model-releasesarxiv-cs-cl

11 Aug 2026

REFRAMED: Towards Realistic Audio Description Generation for Movies

arXiv:2608.09765v1 Announce Type: new Abstract: Audio Description (AD) is a verbal narration of key visual content in videos, enabling access for visually impaired audiences. Unlike standard video cap

ReliableNet: A Chance-Constrained Approach to Trustworthy Classification in Deep Learning

arXiv:2608.09768v1 Announce Type: new Abstract: A prediction that is both confident and wrong is a critical reliability failure because it can bypass abstention and human review precisely when the mod

REMAC: Self-Reflective and Self-Evolving Multi-Agent Collaboration for Long-Horizon Robot Manipulation

arXiv:2503.22122v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) have demonstrated remarkable capabilities in robotic planning, particularly for long-horizon tasks that require

RenderMatte: Exact-Alpha Rendering and Group-Relative Alignment for Image Matting

arXiv:2608.08487v1 Announce Type: new Abstract: Image matting is an essential enabling technology for modern visual content production, where foreground extraction determines the realism and editabili

Reproducing and Stress-Testing Two Approaches to LLM Reasoning Reliability: Test-Time Probability Aggregation and Logic-Representation Editing

arXiv:2608.08514v1 Announce Type: new Abstract: We independently reproduce two recent methods for making large language model (LLM) reasoning more reliable, and stress-test them across domains and mod

Researchers find that feeding a frontier model's encrypted reasoning traces to a weaker model from the same provider can make it output the traces in plaintext (Will Knight/Wired)

Will Knight / Wired: Researchers find that feeding a frontier model's encrypted reasoning traces to a weaker model from the same provider can make it output the traces in plaintext — Researchers devis

model-releasestechmeme

Rethinking 3D Segmentation from Individual LiDAR Scans: Incidence-Aware Sampling on the SIP Benchmark

arXiv:2608.07757v1 Announce Type: new Abstract: 3D scene understanding is increasingly important in construction, yet most methods are developed on curated datasets that do not fully reflect real site

Rethinking Attention Locality in Spiking Transformers

arXiv:2608.08541v1 Announce Type: new Abstract: Spiking Transformers provide a promising paradigm for efficient visual processing with spike-driven computation, yet their Softmax-free Spiking Self-Att

Rethinking Medical Landmark Localization with Prototype Learning-based Progressive Offset Correction

arXiv:2608.09182v1 Announce Type: cross Abstract: Accurate landmark localization in medical images is a fundamental step for quantitative clinical measurement and downstream analysis. Existing localiz

Rethinking Self-Evolving Agents: Do We Still Need Prescribed Optimization Pipelines?

arXiv:2608.09629v1 Announce Type: new Abstract: Self-evolving agents are usually built around prescribed optimization pipelines: the framework decides how to gather evidence, revise a persistent artif

RippleKV: Cross-Layer KV Cache Allocation via Perturbation Propagation

arXiv:2608.08684v1 Announce Type: cross Abstract: Long-context LLM inference is bottlenecked by KV cache memory, yet distributing a limited cache budget across layers remains challenging. Existing met

RISE-RL: Rubric-Informed Selective Exploration for Open-Ended Reinforcement Learning

arXiv:2608.09123v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) for open-ended tasks is challenging because responses must satisfy multidimensional criteria without following a s

RotaryQuant: Fitting 120B MoE Models on Consumer Hardware via Fused Compressed-Space Attention

arXiv:2608.08081v1 Announce Type: cross Abstract: Large mixture-of-experts (MoE) language models with 26--120 billion parameters exceed the memory capacity of consumer devices through three simultaneo

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough

arXiv:2608.07583v1 Announce Type: cross Abstract: Multi-agent LLM systems route among model-backed advisors, yet a deployer rarely knows before shipping whether routing will help at all. Prevailing ro

Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-of-Experts Models

arXiv:2608.07890v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models decouple total parameters from per-token compute, but deployment still requires storing every expert. Recent theory sh

SafeSceneReason: A Multimodal Reasoning Benchmark Connecting Industrial Hazards with Accident Knowledge

arXiv:2608.09230v1 Announce Type: new Abstract: Industrial-safety understanding requires more than detecting workers, equipment, and personal protective equipment. Models must also assess compliance,

SAGE: SLO-Aware Adaptive Retrieval for Production RAG Systems

arXiv:2608.08237v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems in production operate under strict service level objectives (SLOs) on tail latency and infrastructure cos

SAIN: Structure-Aware Interactive Navigation with Active Dialogue Grounding for Mobile Robot

model-releasesarxiv-cs-ro

arXiv:2608.09196v1 Announce Type: new Abstract: Most existing vision-language navigation tasks assume that instructions are complete and unambiguous. However, real-world robots often encounter natural

Same Question, Different Answer? Measuring and Mitigating Prompt Privilege for Equitable AI Access

arXiv:2608.08942v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into healthcare, education, public services, and everyday decision making. They should provide

Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains

arXiv:2608.09873v1 Announce Type: cross Abstract: We introduce Sci-VBench, a comprehensive benchmark for evaluating knowledge- and reasoning-intensive video generation across scientific domains. It co

SciTaRC: A Plan-Annotated Scientific Tabular QA Benchmark for Language Reasoning and Complex Computation

arXiv:2603.08910v2 Announce Type: replace Abstract: We introduce SciTaRC, an expert-authored benchmark for question answering over scientific tables that targets composite, multi-step reasoning. To en

SCTD 3.0: Sonar Common Target Detection in the Wild - A Large-Scale, Multi-Scene Dataset from Real Marine Surveys

arXiv:2608.08106v1 Announce Type: new Abstract: Synthetic Aperture Sonar (SAS) is core for wide-area detection of small underwater targets. However, large-scale, high-quality SAS datasets are scarce,

SDDBMs: Soft Denoising Diffusion Bridge Models

arXiv:2608.08594v1 Announce Type: new Abstract: Diffusion bridge models leverage Doob's (h)-transform to construct stochastic transports between arbitrary endpoint distributions, and have shown strong

Sekai2: From World Exploration to Interactive World Modeling

arXiv:2608.09449v1 Announce Type: new Abstract: Video world models must capture how scenes evolve over time and across viewpoints. Training them for long-horizon generation and camera control therefor

SeqLoc: Beyond the Single Frame for Cross-View Geo-Localization in Feature-Sparse Scenes

arXiv:2608.07835v1 Announce Type: new Abstract: Cross-View Geo-Localization (CVGL) with OpenStreetMap (OSM) performs well in structure-rich urban environments but collapses in feature-sparse scenes su

Shape Mutating Expert Compression:LorExperts and BTExperts

arXiv:2608.07814v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) language models deliver high capacity at low per-token compute, but deploying them cheaply requires compressing their many ex

Shattered Compositionality: Counterintuitive Learning Dynamics of Transformers for Arithmetic

arXiv:2601.22510v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often achieve strong benchmark accuracy yet remain brittle under small distribution shifts. While recent mechanis

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents

arXiv:2608.09885v1 Announce Type: new Abstract: The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, per

SI-Edit: Toward Sketch-Instruction Guided Local Image Editing with Pixel-Level Precision

arXiv:2608.09097v1 Announce Type: new Abstract: Despite rapid advances in generative models, achieving pixel-level precision in sketch-based image editing remains a persistent challenge, particularly

SIMMER: Benchmarking Latent Failures in LLM Executable Planning with a World Model

arXiv:2606.14574v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as planners for autonomous agents in household environments. While existing benchmarks

SkillConsist: Detecting Inconsistencies in Agent Skills via Bidirectional Graph Alignment

arXiv:2608.07639v1 Announce Type: cross Abstract: Agent Skills provide reusable capabilities to LLM agents. Agent Skill inconsistencies can expose undisclosed dangerous behavior or cause wrong Skill s

SkillReason: Reasoning-Enhanced Agent Skill Retrieval for Implicit User Requests

arXiv:2608.08640v1 Announce Type: new Abstract: Large language model agents increasingly rely on reusable skills to extend their capabilities beyond parametric knowl- edge. However, retrieving the app

SkillSentry: Reliable Skill Execution for LLM Agents via Runtime Assurance

arXiv:2608.09253v1 Announce Type: new Abstract: LLM agents are increasingly equipped with skills to perform complex tasks through multi-step reasoning and tool use. Although skills provide reusable pr

SLIM-0.5B: Learning Action-Grounded Predictive Latents for Robot Manipulation

model-releasesarxiv-cs-ro

arXiv:2608.09771v1 Announce Type: new Abstract: Vision-language-action policies rely on large multimodal backbones to jointly perform perception, language conditioning, and action generation at every

Smart Compaction: Predicting Compaction Utility from Lakehouse Table Metadata

arXiv:2608.08639v1 Announce Type: new Abstract: Open lakehouse table formats accumulate small data files over time, which degrades query performance. Deciding when compaction is worthwhile remains thr

Social Gym and SPaRTan: Benchmarking and Improving LLM Social Reasoning via Multi-Agent Game Tournaments

arXiv:2608.09128v1 Announce Type: cross Abstract: LLM agents are increasingly deployed in multi-agent social settings where they must cooperate, negotiate, and adapt to other agents. Measuring and imp

SodaMem: Evidence-Grounded Temporal Graph Memory for LLM Agents

arXiv:2608.08055v1 Announce Type: new Abstract: Large language model (LLM) agents that assist users over weeks of conversation must remember what is currently true, not merely what was once said. Flat

Sources: Nvidia is developing a Nemotron 4 model with 1T+ parameters, up from Nemotron 3 Ultra's 550B parameters but smaller than leading Chinese open models (The Information)

The Information: Sources: Nvidia is developing a Nemotron 4 model with 1T+ parameters, up from Nemotron 3 Ultra's 550B parameters but smaller than leading Chinese open models — Nvidia is doubling down

model-releasestechmeme

Sparks of Cooperative Reasoning: LLMs as Strategic Hanabi Agents

arXiv:2601.18077v3 Announce Type: replace Abstract: Cooperative reasoning under incomplete information remains challenging for both humans and multi-agent systems. The card game Hanabi embodies this c

Sparse corruption in low-rank matrix inference: the PCA benchmark

arXiv:2511.11927v2 Announce Type: replace-cross Abstract: Principal Component Analysis (PCA) is a standard tool for extracting a low-rank signal from noisy observations. It is known that applying PCA

SPECTRA: Pushing the KV Cache Beyond the 2-Bit Cliff via Spectral Transform Coding

arXiv:2608.07915v1 Announce Type: new Abstract: Large language models (LLMs) increasingly read long inputs in the agentic era, from whole documents and codebases to conversations across many turns. Th

Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention

arXiv:2608.07921v1 Announce Type: cross Abstract: We apply Marchenko-Pastur (MP) random matrix theory to pre-trained attention weights in order to separate each projection matrix into a random-like bu

SpikeWorld: Fast-State Adaptation for Frozen Spiking World Models

arXiv:2608.07712v1 Announce Type: cross Abstract: A predictive model receives a self-supervised signal whenever the consequence of an action is observed. Using that signal after deployment is difficul

SPRInG: Continual LLM Personalization via Selective Parametric Adaptation and Retrieval-Interpolated Generation

arXiv:2601.09974v2 Announce Type: replace Abstract: Personalizing Large Language Models typically relies on static retrieval or one-time adaptation, assuming user preferences remain invariant over tim

Stateful CARS: Exact Cross-History Reuse for Policy-Constrained LLM Agents

arXiv:2608.08282v1 Announce Type: new Abstract: Tool-using language-model agents face constraints whose meaning changes with observations and prior actions. We study exact sampling from the model dist

Staying True to the Origin: Continuous Image Stylization with Smooth Transitions

arXiv:2608.08125v1 Announce Type: new Abstract: Recent advances in generative models have achieved remarkable performance in text- and image-conditioned editing. However, preserving the content of a g