Search: “models”

Clinician-Level Agreement Without Clinical Caution: LLM Evaluator Limits in Medical AI Benchmarking

arXiv:2607.01103v1 Announce Type: new Abstract: Open-response evaluation provides stronger clinical validity than multiple-choice benchmarks but creates a scoring bottleneck that motivates automated L

Model Releases

DroneFINE: Domain-Aware Parameter-Efficient Fine-Tuning of Vision-Language Detectors for Drone Images

DGX agent

arXiv:2607.00338v1 Announce Type: new Abstract: Object detection for Unmanned Aerial Vehicles (UAVs) working in open and dynamic environments is a highly challenging task. While Vision-Language Models

model-releasesarxiv-cs-cv

2 Jul 2026

Efficient Multilingual Reasoning Transfer via Progressive Code-Switching

arXiv:2607.00485v1 Announce Type: new Abstract: Large reasoning models (LRMs) have achieved strong reasoning capabilities in English, yet their performance degrades significantly when required to reas

researcharxiv-cs-cl

GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process Supervision

arXiv:2607.01050v1 Announce Type: new Abstract: Recent multimodal large language models (MLLMs) have shown strong cross-modal understanding and coordinate generation abilities in visual grounding. How

Ghost in the Kernel: In-Context Learning with Efficient Transformers via Domain Generalization

arXiv:2607.00479v1 Announce Type: new Abstract: Transformer-based large models have demonstrated remarkable generalization abilities across different tasks by leveraging a context-aware attention modu

GRACE-RAG: Governed Retrieval Architecture for Canonical Evidence Synthesis, Enabling Lightweight Deployment in Closed-Domain Institutional Settings

arXiv:2607.00013v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are widely used in institutional question answering settings where responses must be grounded in authorit

GryphOne: Symbol-Aware Masked Diffusion for Structural Refinement in Offline Handwritten Mathematical Expression Recognition

arXiv:2602.03370v2 Announce Type: replace Abstract: Handwritten mathematical expression recognition (HMER) requires reasoning over diverse symbols and structures, yet autoregressive models struggle wi

Identifying and Resolving Pitfalls of Knowledge-Based VQA Benchmarks: Auditing, Repairing, and Augmenting

arXiv:2607.00159v1 Announce Type: new Abstract: Knowledge-Based Visual Question Answering (KB-VQA) aims to evaluate whether Visual Language Models (VLMs) can retrieve, ground, and reason over external

Information-Regularized Attention for Visual-Centric Reasoning

arXiv:2607.00434v1 Announce Type: new Abstract: Vision-language models (VLMs) have become a paradigm for multimodal learning, yet remain unstable due to object hallucination, weak visual grounding, an

LLM Wikis are being slept on. I argue that creating knowledge bases with LLMs or coding agents is one of the most valuable applications of A…

LLM Wikis are being slept on. I argue that creating knowledge bases with LLMs or coding agents is one of the most valuable applications of AI today. It's about being intentional in building and scalin

model-releasesdair-ai--x

MolSafeEval: A Benchmark for Uncovering Safety Risks in AI-Generated Molecules

arXiv:2607.00464v1 Announce Type: cross Abstract: Current molecular generation benchmarks emphasize task complexity, molecule novelty, and property alignment; they largely overlook a critical concern:

MSQA: A Natively Sourced Multilingual and Multicultural SimpleQA Benchmark

arXiv:2607.00724v1 Announce Type: new Abstract: Multilingual fluency often invites a stronger assumption: a model that can speak a user's language must also understand the culture encoded by that lang

Not All Prediction Targets Keep Training-Free Diffusion Guidance on the Manifold

arXiv:2607.00647v1 Announce Type: new Abstract: Training-free guidance (TFG) steers a pretrained diffusion model toward a desired attribute at inference. To be effective, this guidance must be applied

On the Reliability of Cue Conflict and Beyond

arXiv:2603.10834v4 Announce Type: replace-cross Abstract: Understanding how neural networks rely on visual cues offers a human-interpretable view of their internal decision processes. The cue-conflict

OpFML: Pipeline for ML-based Operational Inference

arXiv:2601.11046v2 Announce Type: replace Abstract: Machine learning models for climate and Earth science are becoming increasingly capable, yet model deployment into operational use remains a largely

researcharxiv-cs-lg

PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking

arXiv:2607.00115v1 Announce Type: new Abstract: This paper explores multi-turn visual reasoning and observes that MLLMs repeatedly fail to localize the target, leading to long, redundant trajectories.

Quantifying the Affective Gap: A Zero-Shot Evaluation of LLMs on Fine-Grained Emotion Taxonomies

arXiv:2607.00968v1 Announce Type: new Abstract: Emotion recognition in natural language is a foundational challenge in affective computing, with critical implications for human-computer interaction, m

Safety

RoboWorld: Fast and Reliable Neural Simulators for Generalist Robot Policy Evaluation

arXiv:2607.01060v1 Announce Type: new Abstract: Video world models are emerging as a scalable alternative for evaluating generalist robot policies, bypassing the physical constraints and engineering b

safetyarxiv-cs-ro

Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains

arXiv:2607.01136v1 Announce Type: cross Abstract: Agent skills package reusable operational knowledge for Large Language Model (LLM) agents, yet as they grow in scope, they become dependency-bearing a

Slope-Guided Mamba and Angular-Refined Transformer for Light Field Super-Resolution

arXiv:2607.00965v1 Announce Type: new Abstract: Light Field Super-Resolution (LFSR) necessitates accurate modeling of spatial-angular correlations while preserving intrinsic 4D ray coherence. However,

researcharxiv-cs-cv

StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning

arXiv:2607.00465v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) rely extensively on Visual Instruction Tuning (VIT) to elicit their multimodal reasoning capabilities. However, w

Local Ai

SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks

arXiv:2607.00053v1 Announce Type: cross Abstract: Large language models (LLMs) embedded in multi-turn agentic harnesses are reshaping software engineering (SWE), but routing every task to a frontier m

local-aiarxiv-cs-ai

Tail-Shape Estimation in LLM Evaluation Is Fragile: A Protocol for Diagnosing False Positives

arXiv:2606.16511v2 Announce Type: replace Abstract: Recent work motivates moving large language model (LLM) evaluation from mean-based to tail-aware metrics, including conditional value-at-risk and ta

TallyTrain: Communication-Efficient Federated Distillation

arXiv:2607.00173v1 Announce Type: new Abstract: Federated learning is bandwidth-bound on two orthogonal axes: model size, which limits how often parameter-averaging methods can afford to merge, and cl

Towards Accurate State Estimation: Motion Dynamics Kalman Filter for 3D Multi-Object Tracking

arXiv:2505.07254v2 Announce Type: replace Abstract: Precise 3D state estimation in multi-object tracking (MOT) is critical for self-driving cars, particularly for objects occluded. Motion modeling in

researcharxiv-cs-cv

TRIE: An Evaluation Framework for Stochastic PDE Surrogates

arXiv:2607.00196v1 Announce Type: new Abstract: Many scientific systems exhibit uncertainty from stochastic forcing, unresolved degrees of freedom, or imperfect observations, making reliable surrogate

Understanding How Humans Inject Knowledge into Machine Learning Workflows through Visual Analytics

arXiv:2607.00969v1 Announce Type: cross Abstract: Visual analytics (VA) plays an increasingly important role in supporting machine learning (ML) workflows. In the field of visualization, such approach

Vitality-Aware Compression for Efficient Image-to-Shape Diffusion Transformers

arXiv:2607.00382v1 Announce Type: new Abstract: We propose the first compression approach for image-to-shape Diffusion Transformers (DiTs) that substantially reduces model size while preserving geomet

researcharxiv-cs-cv

ZO-Act: Efficient Zeroth-Order Fine-Tuning via One-Shot Activation-Informed Low-Rank Subspaces

arXiv:2607.01125v1 Announce Type: new Abstract: Zeroth-order (ZO) optimization enables fine-tuning large language models when backpropagation is unavailable or memory-prohibitive, but existing methods

Tools

8/ Opportunistic Expert Activation: Batch-Aware Expert Routing for Faster Decode Without Retraining (OEA) Paper: https://arxiv.org/abs/2511.…

Opportunistic Expert Activation (OEA) is a batch-aware expert routing technique for mixture-of-experts models that enables faster decoding without requiring model retraining. The method optimizes whic

toolstogether-ai--x

A Systematic Approach to Multi-Agent AI from Advanced Regulatory Control Theory: Safe and Auditable LLM Operator Agents for Process Control

arXiv:2606.30877v1 Announce Type: cross Abstract: Recent literature shows that large language models (LLMs) are useful for general-purpose tasks yet perform poorly on specific domain ones. One reason

Beyond Clean Text: Evaluating Encoder and Decoder Robustness for Bangla Event Detection in Noisy Text

arXiv:2606.30914v1 Announce Type: new Abstract: Event detection (ED) systems are typically evaluated on clean, curated text, leaving their robustness to real-world noise largely unexplored, particular

Beyond Static Prompts: Building Scale-Proof, Polymorphic Multi-Agent Systems with Google's ADK

model-releasesgoogle-cloud-ai

As enterprise generative AI transitions from simple, conversational chatbots to autonomous multi-agent workflows, developers face a critical bottleneck: scale. In a production environment, an enterpri

Local Ai

ComplianceGate: Classifier-Gated Multi-Tier LLM Routing for Inference in Regulated Industries

arXiv:2606.31163v1 Announce Type: cross Abstract: Large language models deployed in regulated industries operate under two constraints: compliance enforcement and cost efficiency. Personally identifia

local-aiarxiv-cs-ai

DynFly: Dynamic-Aware Continuous Trajectory Generation for UAV Vision-Language Navigation in Urban Environments

arXiv:2606.31654v1 Announce Type: cross Abstract: Recent advances in multimodal large models have significantly improved UAV vision-language navigation (UAV-VLN) by enhancing high-level perception and

Energy-Optimal Spatial Iterative Learning within a Virtual Tube

model-releasesarxiv-cs-ro

arXiv:2606.31487v1 Announce Type: new Abstract: Due to the limited endurance of embedded energy sources such as lithium-polymer (LiPo) batteries, the flight duration and operational range of unmanned

Evidence Triangulation for Multimodal Fact-Checking in the Wild

arXiv:2606.31367v1 Announce Type: cross Abstract: The proliferation of multimedia content on social platforms has fueled multimodal misinformation, where images are used to reinforce false claims. Con

Safety

Evo-PI: Aligning Medical Reasoning via Evolving Principle-Guided Supervision

arXiv:2606.31800v1 Announce Type: new Abstract: Despite recent progress, the reasoning capabilities of large multimodal language models (MLLMs) remain fundamentally constrained by static supervision,

safetyarxiv-cs-ai

FinPersona-Bench: A Benchmark for Longitudinal Psychometric Stability of Autonomous Financial Agents

arXiv:2606.31522v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous financial agents initialized with explicit behavioral mandates such as 'preserve

good post on the value of knowing whats going on in your harness 'For agents within an actual product, I have gravitated to using LangChain …

model-releasesharrison-chase--x

good post on the value of knowing whats going on in your harness 'For agents within an actual product, I have gravitated to using LangChain DeepAgents' The frontier model lab harnesses are amazing - d

Local Ai

Histogram-constrained Image Generation

arXiv:2606.31683v1 Announce Type: cross Abstract: Diffusion models have emerged as a dominant paradigm in generative modeling, enabling high-fidelity sampling from complex data distributions. Despite

local-aiarxiv-cs-ai

M3CoTBench: Benchmark Chain-of-Thought of MLLMs in Medical Image Understanding

arXiv:2601.08758v4 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) reasoning has proven effective in enhancing large language models by encouraging step-by-step intermediate reasoning, a

MECoBench: A Systematic Study of Multimodal Agent Collaboration in Embodied Environments

arXiv:2606.31966v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) have strong potential as embodied agents, but their ability to collaborate in visually grounded enviro

Medical Image Spatial Grounding with Semantic Sampling

arXiv:2603.14579v3 Announce Type: replace Abstract: Vision language models (VLMs) have shown significant promise in visual grounding for images as well as videos. In medical imaging research, VLMs rep

Nemotron 3 Ultra is taking off on Together AI 🚀 In just days, it's climbed to 35B tokens/day on @OpenRouter. That's the community voting wi…

model-releasestogether-ai--x

Nemotron 3 Ultra is taking off on Together AI 🚀 In just days, it's climbed to 35B tokens/day on @OpenRouter. That's the community voting with their tokens for open models that are fast, efficient, and

No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs

arXiv:2606.31933v1 Announce Type: new Abstract: We introduce VidPair-Halluc, a new benchmark for evaluating video hallucination in large video models (LVMs) under rigorous and controlled conditions. U

Applications

Probing Memorization of Tabular In-Context Learning

arXiv:2606.31208v1 Announce Type: new Abstract: Large tabular models (LTMs), i.e., tabular foundation models leveraging in-context learning (ICL), achieve state-of-the-art performance on tabular tasks

applicationsarxiv-cs-lg

Sequential RC-TGAN: Generating Relational Time Series with Spectral Envelope Loss

arXiv:2606.31904v1 Announce Type: new Abstract: The generation of synthetic relational databases often involves modeling complex temporal dynamics, such as transaction logs or event sequences. A signi