text · 相关事件
相关事件
Consistent Yet Wrong: Evidence Insensitivity in Spatial Vision-Language Models
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Plan2Map: A Multimodal Benchmark for Document-Grounded Geospatial Boundary Reconstruction from Planning Records
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Diagnosis of Human Object Interaction Detectors for Real World Educational Applications
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Diagnosis of Human Object Interaction Detectors for Real World Educational Applications
2026-06-03BREAKTHROUGH影响: HIGH
Hand Trajectory Fusion for Egocentric Natural Language Query Grounding
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
TGV-KV: Text-Grounded KV Eviction for Vision-Language Models
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Zero-Shot 3D Question Answering via Hierarchical View-to-Token Transportation
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
SRENet: Spectral Re-Entry Network for Point Cloud Action Recognition
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
MemoGen: Can Past Experience Improve Future Text-to-Image Generation?
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
$A^2$: Smaller Self-Supervised ViTs Localize Better than Larger Ones
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation
2026-06-03OPEN_SOURCE影响: MEDIUM
P\textsuperscript{2}-DPO: Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Beyond Semantics: Modeling Factual and Affective Perceptual Experiences from Vision-Language Data
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
From 3D Perception to Safety Reasoning: A Graph-Based Framework for Real-Time Underground Mine Monitoring
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Towards Characterizing Scientific Image Utility and Upgradability
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Mixed-Modality Dual Face-Hair Retrieval
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
PersistGS: Differentiable Physics for Object Permanence in 4D Gaussian Splatting
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
PHAF-Personalized Hand Avatars in a Flash
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Low-Frequency Shortcuts in Texture-Driven Visual Learning
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Knowledge-Preserved Model Tuning in Null-Space for Robust Spatio-Temporal Video Grounding
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
\textsc{CR-Seg}: Attention-Guided and CoT-Enhanced Coarse-to-Refined Reasoning Segmentation
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
When Attention Collapses: Stage-Aware Visual Token Pruning from Structure to Semantics
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Text-to-Image Models Need Less from Text Encoders Than You Think
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Qwen-Image-Flash: Beyond Objective Design
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Training-Free Multi-Concept LoRA Composition with Prompt-Aware Weighting
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
TeX-1500: A Paired Real-World LWIR Hyperspectral Dataset and Benchmark for Temperature-Emissivity-Texture Decomposition
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Where Do We (Not) Need Temporal Context in Low-Resource Video Task Adaptation?
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Unified Video-Action Joint Denoising for Dexterous Action and Data Generation
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Visual Instruction Tuning Aligns Modalities through Abstraction
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Adaptive Causal Alignment for High-Confidence Adversarial Training
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
VLESA: Vision-Language Embodied Safety Agent for Human Activity Monitoring
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Demo2Tutorial: From Human Experience to Multimodal Software Tutorials
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
AAD-1: Asymmetric Adversarial Distillation for One-Step Autoregressive Video Generation
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
AAD-1: Asymmetric Adversarial Distillation for One-Step Autoregressive Video Generation
2026-06-03BREAKTHROUGH影响: HIGH
BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
An Improved Method for Personalizing Diffusion Models
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
CREward: A Type-Specific Creativity Reward Model
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
PubTables-v2: A new large-scale dataset for full-page and multi-page table extraction
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Edge-Aware and Content-Adaptive Infrared Gas Leak Detection for Industrial Safety Monitoring
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Edge-Aware and Content-Adaptive Infrared Gas Leak Detection for Industrial Safety Monitoring
2026-06-03REGULATION影响: MEDIUM
Best of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Cryo-Bench: Benchmarking Foundation Models for Cryosphere Applications
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Ref-DGS: Reflective Dual Gaussian Splatting
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
SJD-PAC: Accelerating Speculative Jacobi Decoding via Proactive Drafting and Adaptive Continuation
2026-06-03PRODUCT_LAUNCH影响: MEDIUM
Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models
2026-06-03PRODUCT_LAUNCH影响: MEDIUM