Search: “models”

Diffusing in the Right Space: A Systematic Study of Latent Diffusability

arXiv:2606.03578v1 Announce Type: new Abstract: Latent diffusion models leverage visual tokenizers to compress images into latent spaces for efficient generative modeling. However, better reconstructi

researcharxiv-cs-cv

Efficient ASR Training with Conversations that Never Happened

DGX agent

arXiv:2606.03957v1 Announce Type: cross Abstract: Conversational ASR for lower-resource languages and niche domains is limited by the scarcity of domain-matched multi-speaker training data. We propose

model-releasesarxiv-cs-ai

3 Jun 2026

Efficient Hyperparameter Optimization for LLM Reinforcement Learning

arXiv:2606.03073v1 Announce Type: cross Abstract: Reinforcement learning (RL) for large language models (LLMs) is highly sensitive to hyperparameter configurations, making hyperparameter optimization

researcharxiv-cs-ai

Local Ai

FLARE: Fine-Grained Diagnostic Feedback for LLM Code Refinement

arXiv:2606.03852v1 Announce Type: cross Abstract: Large language models often generate code with bugs. Existing methods rely on feedback signals such as test failures and self-critiques to iteratively

local-aiarxiv-cs-ai

FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences

arXiv:2606.03330v1 Announce Type: cross Abstract: Literature reveals that a Large Language Model's (LLM) behavior is not only conditioned by its original weights but also its instance-level parameters

researcharxiv-cs-ai

FSA-GRPO: Teaching Auditory LLMs to Use Few-shot Demonstrations

arXiv:2606.02615v1 Announce Type: cross Abstract: Few-shot prompting provides an effective way to adapt auditory large language models to low-resource tasks such as children's speech recognition. Howe

researcharxiv-cs-ai

GFFMERGE: Efficient Merging of Graph Neural Force Fields and Beyond

arXiv:2606.03232v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) have revolutionized Neural Force Fields for atomistic simulations, achieving near-quantum accuracy at reduced cost, yet a

GN0: Toward a Unified Paradigm for Generation, Evaluation, and Policy Learning in Visual-Language Navigation

model-releasesarxiv-cs-ro

arXiv:2606.03682v1 Announce Type: new Abstract: Embodied navigation connects intelligent agents with the physical world and is fundamental for general robotic intelligence. Limited availability and qu

Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs

model-releasesarxiv-cs-cl

arXiv:2606.02628v1 Announce Type: cross Abstract: We investigate whether open-source LLMs encode a linearly separable truthfulness signal in their hidden states, and at which network depth this signal

Hedge-Bench: Benchmarking Agents on Hard, Realistic Tasks Pertaining to Financial Reasoning

arXiv:2606.03918v1 Announce Type: new Abstract: AI agents can increasingly handle the mechanical tasks of financial analysis: retrieving documents, calculating formulas, updating spreadsheets. The har

Hint-Guided Diversified Policy Optimization for LLM Reasoning

arXiv:2606.03021v1 Announce Type: new Abstract: Recent developments in Large Language Models (LLMs) have showcased impressive reasoning capabilities, with Reinforcement Learning with Verifiable Reward

safetyarxiv-cs-cl

Honesty in Causal Forests: When It Helps and When It Hurts

arXiv:2506.13107v4 Announce Type: replace Abstract: Causal forests estimate how treatment effects vary across individuals, guiding personalized interventions in areas like marketing, operations, and p

JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation

arXiv:2606.03168v1 Announce Type: new Abstract: While instruction-based video editing has seen significant progress, joint audio-visual editing remains constrained by the absence of dedicated datasets

KForge: LLM-Driven Cross-Platform Kernel Generation for AI Accelerators

arXiv:2606.02963v1 Announce Type: new Abstract: Production inference increasingly targets a heterogeneous mix of accelerators. Agentic pipelines interleave reasoning, tool calls, and multi-agent coord

KletterMix: Climbing Toward High-Quality German Pretraining Data

arXiv:2606.03773v1 Announce Type: new Abstract: High-quality pretraining data is a central ingredient in modern language models, but German-language resources remain far less developed than their Engl

researcharxiv-cs-cl

KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem

arXiv:2602.20217v2 Announce Type: replace-cross Abstract: Self-speculative decoding (SSD) accelerates LLM inference by skipping layers to create an efficient draft model, yet existing methods often re

applicationsarxiv-cs-ai

LAP: An Agent-to-Instrument Protocol for Autonomous Science

arXiv:2606.03755v1 Announce Type: new Abstract: Autonomous science is moving from demonstration to infrastructure. Large language model agents now plan experiments, and self-driving laboratories execu

MedCUA-Bench: A Screenshot-Only Benchmark for Clinical Computer-Use Agents

arXiv:2606.03203v1 Announce Type: new Abstract: Computer-use agents could automate repetitive screen-based clinical work, but their reliability in medical graphical user interfaces remains largely unv

MuLoCo: Muon is a practical inner optimizer for DiLoCo

arXiv:2505.23725v3 Announce Type: replace Abstract: DiLoCo is a powerful framework for training large language models (LLMs), enabling larger optimal batch sizes and increased accelerator utilization

Multi-Modal Machine Learning for Breast Cancer Recurrence Prediction

arXiv:2606.02892v1 Announce Type: new Abstract: Breast cancer recurrence, a leading cause of long-term mortality among survivors, requires timely and accurate risk assessment to guide follow-up care a

Neuron Populations Exhibit Divergent Selectivity with Scale

arXiv:2606.03990v1 Announce Type: cross Abstract: We investigate whether neuron populations within neural networks evolve predictably with scale, extending scaling laws beyond macroscopic observables

applicationsarxiv-cs-cl

On the Persistent Effects of Lexicality in Large Language Mod

arXiv:2606.02750v1 Announce Type: new Abstract: Representations extracted from large language models (LLMs) play an important role in many downstream applications. However, the structure of these repr

applicationsarxiv-cs-cl

PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training

arXiv:2606.03264v1 Announce Type: new Abstract: We introduce PaddleOCR-VL-1.6, an upgraded compact document parsing model built upon PaddleOCR-VL-1.5. Although PaddleOCR-VL-1.5 establishes a strong 0.

researcharxiv-cs-cv

PieArena: Ranking and Profiling Language Agents in Realistic Negotiation Scenarios

arXiv:2602.05302v3 Announce Type: replace Abstract: We present an in-depth evaluation of LLMs' ability to negotiate, a central business task requiring strategic reasoning, theory of mind, and economic

Principled Reflection Separation via Nonlinear Superposition and Feature Interaction

arXiv:2606.02831v1 Announce Type: new Abstract: Single-image reflection separation is fundamentally challenged by the entanglement of transmission and reflection layers under complex image formation p

applicationsarxiv-cs-cv

Psi-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialogues

arXiv:2606.02754v1 Announce Type: new Abstract: Personalization is a crucial capability of modern language agents. However, current research primarily positions personalized agents as passive responde

Qift: Shift-Friendly No-Zero W2 Post-Training Quantization for Rotated W2A4/KV4 LLM Inference

arXiv:2606.02823v1 Announce Type: new Abstract: Two-bit weight quantization is attractive for memory-efficient LLM inference, but the standard W2 level set {-2,-1,0,+1} often collapses under aggressiv

RMPrior: Bridging Propagation Priors and Diffusion Refinement for Efficient Radio Map Construction

arXiv:2606.03074v1 Announce Type: new Abstract: Diffusion models achieve high-fidelity radio map construction through iterative denoising, yet their sampling cost limits practicality in dynamic wirele

RobotValues: Evaluating Household Robots When Human Values Conflict

arXiv:2606.03312v1 Announce Type: cross Abstract: While household robots are often evaluated based on task completion, everyday domestic environments involve value-conflicting situations in which robo

Sample-Size Scaling of the African Languages NLI Evaluation

model-releasesarxiv-cs-cl

arXiv:2606.03219v1 Announce Type: new Abstract: African languages have very little labelled data, and it is unclear if augmenting the quantity of annotation data reliably enhances downstream performan

Strongly Polynomial Time Complexity of Policy Iteration for L_infty Robust MDPs

arXiv:2601.23229v2 Announce Type: replace Abstract: Markov decision processes (MDPs) are a fundamental model in sequential decision making. Robust MDPs (RMDPs) extend this framework by allowing uncert

T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation

arXiv:2512.21094v2 Announce Type: replace Abstract: Text-to-Audio-Video (T2AV) generation aims to synthesize temporally coherent video and semantically synchronized audio from natural language, yet it

TalkPlayData 2: An Agentic Synthetic Data Pipeline for Multimodal Conversational Music Recommendation

arXiv:2509.09685v5 Announce Type: replace-cross Abstract: We present TalkPlayData 2, a synthetic dataset for multimodal conversational music recommendation generated by an agentic data pipeline. In th

TIDFormer: Exploiting Temporal and Interactive Dynamics Makes A Great Dynamic Graph Transformer

arXiv:2506.00431v2 Announce Type: replace Abstract: Due to the proficiency of self-attention mechanisms (SAMs) in capturing dependencies in sequence modeling, several existing dynamic graph neural net

What Benchmarks Don't Measure: The Case for Evaluating Abstention Competence in Autonomous Agents

arXiv:2606.02965v1 Announce Type: new Abstract: Benchmarks for autonomous agents measure whether agents complete tasks, yet this framing is systematically blind to whether an agent should have proceed

A Systematic Benchmark of Intraoperative Ultrasound-to-MR Synthesis for Brain Tumour Surgery

arXiv:2606.00630v1 Announce Type: new Abstract: Intraoperative ultrasound (ioUS) is a versatile, cost-effective modality in brain tumour surgery, but its interpretation is difficult: acquisition plane

A Task-Centric Theory for Iterative Self-Improvement with Easy-to-Hard Curricula

arXiv:2602.10014v3 Announce Type: replace Abstract: Iterative self-improvement fine-tunes an autoregressive large language model (LLM) on reward-verified outputs generated by the LLM itself. In contra

Tutorials

AdaKernel: Learning Adaptive Kernel Parameters for Spatiotemporal Graph Neural Networks

arXiv:2606.01283v1 Announce Type: new Abstract: Modeling spatial dependencies is central to spatiotemporal data analysis using Graph Neural Networks (GNNs). Traditional methods rely on distance-based

tutorialsarxiv-cs-lg

Local Ai

AEyeDE: An Attention-Based Attribution Framework for AI-Generated Text Detection

arXiv:2606.00016v1 Announce Type: cross Abstract: Detecting AI-generated text is becoming increasingly challenging as modern language models approach human-level fluency and can evade detectors that r

local-aiarxiv-cs-ai

AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations

arXiv:2606.02240v1 Announce Type: cross Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, S

APE: Agentic Prompt Enhancer for Image Generation and Editing

arXiv:2606.00204v1 Announce Type: new Abstract: Natural language has become a powerful interface for image generation and editing, yet text-guided visual systems remain highly sensitive to prompt form

ASE-26: a curriculum for agentic software engineering as a discipline

arXiv:2606.01152v1 Announce Type: cross Abstract: The work of a professional software engineer has begun to consist, increasingly, of directing agents rather than writing code, and the empirical evide

Beyond Static Gaussians: An Empirical Investigation of Architectural Paradigms for Dynamic 3D Scene Reconstruction

arXiv:2606.00452v1 Announce Type: new Abstract: Dynamic scene reconstruction via 3D Gaussian Splatting (3DGS) has emerged as a compelling approach for representing evolving environments, yet understan

Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance

arXiv:2606.00305v1 Announce Type: cross Abstract: On-Policy Distillation (OPD) improves large language model reasoning by training a student model on trajectories sampled from its own policy under tea

Bridging Requirements and Architecture: Multi-Agent Orchestration with External Knowledge and Hierarchical Memory

arXiv:2606.01385v1 Announce Type: cross Abstract: Software architecture design is a critical yet inherently complex and knowledge-intensive phase that requires balancing competing quality attributes a

CardioLens: Revealing the Clinical Reality Gap of MLLMs via Multi-Sequence Cardiac MRI Evaluations

arXiv:2606.00123v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have shown strong performance on public medical benchmarks, yet existing evaluations often remain weak proxie

applicationsarxiv-cs-ai

ChatUMM: Robust Context Tracking for Conversational Interleaved Generation

arXiv:2602.06442v2 Announce Type: replace Abstract: Unified multimodal models (UMMs) have achieved remarkable progress yet remain constrained by a single-turn interaction paradigm, effectively functio

researcharxiv-cs-cv

ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree

arXiv:2606.01494v1 Announce Type: cross Abstract: Agent skills extend AI agents with reusable instructions, tools, scripts, references, and workflows, establishing a security boundary distinct from bo