All entries

Findings of the MAGMaR 2026 Shared Task

arXiv:2606.12295v1 Announce Type: cross Abstract: This overview paper presents the results of the shared task for the second workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMa

researcharxiv-cs-cl

Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training

arXiv:2606.11854v1 Announce Type: cross Abstract: There are two main Parameter-Efficient Fine-Tuning (PEFT) techniques for Large Language Models (LLMs). While Low-Rank Adaptation (LoRA) introduces add

model-releasesarxiv-cs-ai

11 Jun 2026

Tutorials

FitVTON: Fit-aware Virtual Try-On via Body-Garment Size Control

arXiv:2606.12012v1 Announce Type: new Abstract: While diffusion-based virtual try-on has achieved impressive visual realism, most methods treat the task as 2D inpainting, prioritizing texture preserva

tutorialsarxiv-cs-cv

Fixed-Parameter Tractability of Private Synthetic Data Generation

model-releasesarxiv-cs-lg

arXiv:2606.11283v1 Announce Type: cross Abstract: We study the problem of generating synthetic data under differential privacy. We establish fixed-parameter tractability (FPT) for this problem where t

Applications

FlexiBrain: Resolution-Agnostic Voxel-Level Encoding for Native fMRI

arXiv:2606.11500v1 Announce Type: cross Abstract: The success of large-scale deep learning models in neuroscience is fundamentally constrained by severe data heterogeneity. Native fMRI data aggregated

applicationsarxiv-cs-lg

Flow Matching with In-Context Priors for Out-of-Distribution Brain Dynamics

arXiv:2606.11833v1 Announce Type: new Abstract: Flow matching and diffusion models enable conditional generation across domains ranging from images to proteins, with recent extensions to out-of-distri

researcharxiv-cs-lg

FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse

arXiv:2606.11290v1 Announce Type: cross Abstract: Large Language Model (LLM)-based multi-agent systems are increasingly powerful, but current agentic workflow optimization paradigms make an unsatisfyi

agentsarxiv-cs-ai

Tutorials

FOCUS: DLLMs Know How to Tame Their Compute Bound

arXiv:2601.23278v2 Announce Type: replace-cross Abstract: Diffusion Large Language Models (DLLMs) offer a compelling alternative to Auto-Regressive models, but their deployment is constrained by high

tutorialsarxiv-cs-cl

Applications

FOCUS on Contamination: Hydrology-Informed Noise-Aware Learning for Geospatial PFAS Mapping

arXiv:2502.14894v5 Announce Type: replace-cross Abstract: Per- and polyfluoroalkyl substances (PFAS) are persistent environmental contaminants with significant public health impacts, yet large-scale m

applicationsarxiv-cs-ai

Forecasting Future Behavior as a Learning Task

model-releasesarxiv-cs-ai

arXiv:2606.11445v1 Announce Type: new Abstract: Trust in an AI system is often anchored by explanations of how it works, which one then uses to forecast its behavior on new inputs. For large reasoning

FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents

arXiv:2606.12087v1 Announce Type: new Abstract: Training deep search agents requires verifiable questions whose answers remain unavailable until sufficient evidence has been acquired through search. E

researcharxiv-cs-cl

Fourier Features Let Agents Learn High Precision Policies with Imitation Learning

arXiv:2606.12334v1 Announce Type: new Abstract: High-precision robotic manipulation requires fine-grained spatial reasoning that is often difficult to achieve with RGB-only policies due to depth ambig

safetyarxiv-cs-lg

FreeBridge: Variational Schrodinger Bridges for Cellular Transition Dynamics

arXiv:2606.11286v1 Announce Type: cross Abstract: High-content imaging assays quantify cellular responses to chemical and genetic perturbations, yet continuous trajectories of individual cells are uno

FreqKD: Frequency-Decoupled Cross-Modal Knowledge Distillation for Infrared Object Detection

arXiv:2606.11572v1 Announce Type: new Abstract: Transfer learning from large-scale RGB foundation models to infrared (IR) imagery through knowledge distillation (KD) remains challenging due to fundame

safetyarxiv-cs-cv

From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion

arXiv:2606.12303v1 Announce Type: new Abstract: Multimodal image fusion aims to integrate complementary information from different modalities into a fused image that preserves rich local details while

researcharxiv-cs-cv

From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data

arXiv:2606.07537v1 Announce Type: cross Abstract: Large language models hallucinate--producing fluent, confident, factually wrong outputs--with a consistency that persists across generations and scale

From Awareness to Action: Understanding and Overcoming the Research-Practice Gap in Algorithmic Fairness for Public Health

arXiv:2606.11214v1 Announce Type: cross Abstract: Algorithmic fairness is essential for responsible ML-driven public health research, yet its practical implementation remains limited. To investigate t

From Consumption to Reflection: Designing Human-AI Relations for Stable Reasoning

arXiv:2606.11195v1 Announce Type: cross Abstract: Large language models (LLMs) have transformed how humans access information, but not how we reason with it. Their fluency accelerates consumption whil

From Content to Knowledge: Lightning Fast Long-Video Understanding with Neural Knowledge Representations

model-releasesarxiv-cs-cv

arXiv:2606.11913v1 Announce Type: new Abstract: We propose a new paradigm for long video understanding by treating a long video as a Neural Knowledge Representation (NKR). NKR represents video content

From Correspondence to Actions: Human-Like Multi-Image Spatial Reasoning in Multi-modal Large Language Models

arXiv:2602.08735v3 Announce Type: replace Abstract: While multimodal large language models (MLLMs) have made substantial progress in single-image spatial reasoning, multi-image spatial reasoning, whic

safetyarxiv-cs-cv

From Explicit Elements to Implicit Intent: A Predefined Library for Auditable Behavioral Inference

arXiv:2606.11207v1 Announce Type: new Abstract: We present SemantiClean, a modular framework for extracting structured semantic signals from e-commerce session data and driving pluggable inference tar

From Nominal Intensity to Equivalent Rainfall: A Path-Based Credibility Evaluation Framework for Simulated Rainfall in Autonomous-Driving Perception Tests

arXiv:2606.11989v1 Announce Type: new Abstract: Credible simulated-rainfall conditions are essential for identifying perception-system boundaries and supporting SOTIF-oriented risk assessment in autom

agentsarxiv-cs-cv

From Persistence to Survival: Hypothesis Testing, Effect Sizes and Vectorisation for Topological Features

arXiv:2606.11911v1 Announce Type: cross Abstract: Persistence diagrams are common representations in topological data analysis, but they do not naturally live in a vector space, and the statistical to

researcharxiv-cs-lg

From Prompts to Tokens: Internalizing Causal Supervision in Vision-Language Model for Multi-Image Causal Reasoning

arXiv:2606.11745v1 Announce Type: cross Abstract: Visual causal reasoning is essential for understanding and intervening in the physical world, requiring identification of causal variables from visual

Hardware

From Simulation to Real-World: An In-Field 6D Pose Dataset and Baseline for Robotic Strawberry Harvesting

arXiv:2606.11381v1 Announce Type: new Abstract: Robotic strawberry harvesting requires precise 6D pose estimation; however, collecting 6D pose ground truth in real agricultural fields is inherently ch

hardwarearxiv-cs-cv

Applications

From Uniform to Learned Graph Priors: Diffusion for Structure Discovery

arXiv:2606.11831v1 Announce Type: cross Abstract: Neural relational inference (NRI) methods discover interaction graphs from trajectories through variational reasoning on discrete potential edges. How

applicationsarxiv-cs-ai

FronTalk: Benchmarking Front-End Development as Conversational Code Generation with Multi-Modal Feedback

model-releasesarxiv-cs-cl

arXiv:2601.04203v2 Announce Type: replace Abstract: We present FronTalk, a benchmark for front-end code generation that pioneers the study of a unique interaction dynamic: conversational code generati

Local Ai

Frozen Foundation-Model Embeddings Discard Small-Lesion Signal in Chest Radiography: Implications for Pre-Deployment Evaluation

arXiv:2606.11606v1 Announce Type: new Abstract: Frozen vision-transformer (ViT) foundation-model embeddings increasingly serve as the substrate for downstream chest-radiography (CXR) pipelines, yet wh

local-aiarxiv-cs-cv

Frozen Multimodal Embeddings for Personality and Cognitive Ability Assessment in Asynchronous Video Interviews

arXiv:2606.11930v1 Announce Type: cross Abstract: Predicting psychological traits from asynchronous video interviews (AVIs) is a challenging multimodal learning problem because labeled datasets are li

Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization

arXiv:2606.12016v1 Announce Type: cross Abstract: Model post-training, and in particular reinforcement learning (RL), is one of the primary mechanisms by which developers can shape models' values and

Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions

arXiv:2509.10303v2 Announce Type: replace-cross Abstract: Online reinforcement learning (RL) approaches have demonstrated strong performance on Job Shop Scheduling (JSP) and Flexible JSP (FJSP) proble

Geometric bias in eigenspace perturbation under random heterogeneous noise

arXiv:2606.11263v1 Announce Type: cross Abstract: Spectral methods rely fundamentally on the stability of principal eigenspaces under random perturbations. Classically, this stability is quantified by

safetyarxiv-cs-lg

Geometric Metrics and LLMs: What They Measure and When They Work

arXiv:2509.25359v2 Announce Type: replace-cross Abstract: We present a systematic stress-test of geometric metrics for LLM evaluation. Rank-based geometric properties of internal representations have

Geometry of Reason: Spectral Signatures of Valid Mathematical Reasoning

arXiv:2601.00791v2 Announce Type: replace-cross Abstract: Verifying whether a language model is genuinely reasoning or pattern-matching remains an open problem: learned verifiers are expensive, and ou

GLACIER: A Multimodal Student-Teacher Foundation Model for Molecular Property Prediction

arXiv:2606.11382v1 Announce Type: new Abstract: Deep learning models facilitate the discovery of molecules with tailored properties among billions of candidate compounds. However, the computational bu

safetyarxiv-cs-lg

Goal-Autopilot: A Verifiable Anti-Fabrication Firewall for Unattended Long-Horizon Agents

arXiv:2606.11688v1 Announce Type: cross Abstract: Long-horizon LLM agents are not trusted to run unattended: with no human watching, they confidently report success they never verified. We treat hones

agentsarxiv-cs-ai

Google open-sources speedy DiffusionGemma text diffusion model

model-releasessiliconangle

Google LLC today released DiffusionGemma, a large language model based on an emerging machine learning approach known as text diffusion. The company says the algorithm can generate text four times fas

GPO: Learning from Critical Steps to Improve LLM Reasoning

arXiv:2509.16456v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in various domains, showing impressive potential on different tasks. Recently, reasoning LLMs hav

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

arXiv:2606.11817v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they may be misused to produce malicious code. Meanwhile

GraphInfer-Bench: Benchmarking LLM's Inference Capability on Graphs

model-releasesarxiv-cs-cl

arXiv:2606.11562v1 Announce Type: cross Abstract: Graph analysis underlies many applications whose answers cannot be looked up in a single record or retrieved along a path: laundering rings, drug repu

GraspLLM: Towards Zero-Shot Generalization on Text-Attributed Graphs with LLMs

model-releasesarxiv-cs-cl

arXiv:2606.11898v1 Announce Type: new Abstract: Research on Text-Attributed Graphs (TAGs) has gained significant attention recently due to its broad applications across various real-world data scenari

Grounding Computer Use Agents on Human Demonstrations

model-releasesarxiv-cs-ai

arXiv:2511.07332v2 Announce Type: replace-cross Abstract: Building reliable computer-use agents requires grounding: accurately connecting natural language instructions to the correct on-screen element

Gumbel-BEARD: Automatic Layer Selection for Self-Supervised Adaptation of Whisper in Low-Resource Domains

arXiv:2606.11429v1 Announce Type: cross Abstract: Speech foundation models often struggle in low-resource domains due to domain mismatch and data scarcity. We propose Gumbel-BEARD, a domain adaptation

researcharxiv-cs-cl

Local Ai

HAMNO: A Hierarchical Adaptive Multi-scale Neural Operator with Physics-Informed Learning for Dynamical Systems

arXiv:2606.11963v1 Announce Type: new Abstract: Neural operators provide a powerful framework for learning solution mappings of partial differential equations directly in function space. However, many

local-aiarxiv-cs-lg

Harness In-Context Operator Learning with Chain of Operators

arXiv:2606.12318v1 Announce Type: cross Abstract: Neural operators approximate mappings between function spaces, but often generalize poorly to other operators and usually require fine-tuning or retra

Hello from Code with Claude Tokyo!!

model-releasesboris-cherny--x

This post appears to be from Boris Cherny announcing or sharing content related to 'Code with Claude Tokyo,' likely a coding event, workshop, or community initiative involving Claude AI in Tokyo. The

Hermes Agent sets you free

Nous Research announced Hermes Agent, a system designed to provide greater autonomy and flexibility for AI agents in task execution and decision-making. The post likely highlights how this agent frame

agentsnous-research--x

HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-Distillation

arXiv:2606.11559v1 Announce Type: new Abstract: Reinforcement learning typically improves multi-turn agent capabilities through the terminal outcome of the trajectories, which makes it difficult to de