AI News Archive: June 30, 2026 — Part 23
Sourced from 500+ daily AI sources, scored by relevance.
- BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding
Speculative decoding accelerates inference by using a lightweight draft model to generate candidate tokens in parallel, and are then verified by the target model, enabling lossless acceleration. Recently, diffusion-based speculative decoding further improves parallelism by generating multiple tokens...
- Andy Anxiety & Stress Tracker
Free anxiety tracker. Spot your triggers, not just your mood
- The Decomposition Is the Fingerprint: Per-Component Identity for Agent Skills
AI agents increasingly acquire and execute skills at runtime: bundles of prompt instructions, executable code, and tool declarations fetched from marketplaces and other agents. Governing them needs a stable notion of skill identity, yet cryptographic hashing is engineered to destroy the very similar...
- Gated Multi-Graph Fusion via Graph Attention Networks for Alzheimer's Disease Detection
Spontaneous speech is a vital non-invasive biomarker for Alzheimer's Disease (AD), yet many systems overlook non-linear structural disruptions and clinical heterogeneity in pathological language. We propose a Multi-View Gated Graph Attention Network that transcribes audio via Automatic Speech Recogn...
- SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE
We present a zero-shot, training-free and optimization-free framework for generating 360 panoramic images and videos by directly injecting spherical priors into pre-trained diffusion transformers. Existing methods either rely on costly fine-tuning on scarce panoramic data that limits generalization,...
- Automated Background Swapping for Robustness against Spurious Backgrounds
Classifiers based on Deep Neural Networks exhibit strong performance across domains, yet can fail catastrophically if they rely on spurious correlations, i.e., features that are predictive of the target label in the training data but are not causally linked and thus fail to generalize. For the visio...
- CoMet: Context and Multiplicity Decomposition for Multimodal Uncertainty Estimation
Uncertainty estimation has been a long-standing challenge in AI models; it amounts to "knowing what you don't know," and metacognition is notoriously difficult even for humans (cf. the Dunning-Kruger effect). Although it is still far from solved even in simpler classification systems, tackling it in...
- Reviio
AI auto-reply & translation for Google Maps reviews
- RecruiterVibe AI
Enjoy the True Vibe of Automated Hiring.
- Beatrium — Beat-Synced Music Visualizer
Endless AI animations that sync to the music you're playing
- AIdatalOOks
For all your Bussiness Analytics
- Genie
After-hours AI receptionist that books jobs while you sleep
- UseLoveia
A IA brasileira que transforma emoção em palavra certa
- Hermetic AI
Hermetic AI is a software development company.
- MarketiQ Ai
Your Marketing Automation Co-Pilot
- Write Ababil 360
Autonomous AI engine to design, write, and export KDP-ready.
- Wellzy
Therapy AI Free for 24/7 Mental Support | Wellzy
- Claude Prompt Generator
Get perfect Claude prompts for your business
- LE LAB IMMO
AI tools for real estate professionals in France.
- crisprmart.ir کریسپرمارت
ابزارهای مخصوص کریسپر و ژنتیک با هوش مصنوعی
- E-Trust
Smart AI agent that automates emails and meeting scheduling
- TestimonialDrop
Collect customer reviews in 60s — AI turns them into content
- ParseToSheet
Fill your Excel template from a PDF with AI
- lidito
Turn long videos into viral clips with AI
- ToolboxHub
The only toolbox you need — 50+ free tools, zero signup need
- CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts
Chain-of-thought (CoT) reasoning has enabled multi-modal large language models (MLLMs) to tackle complex visual reasoning tasks by generating explicit intermediate reasoning steps in natural language. However, this text-based reasoning paradigm is inherently slow at inference time with even thousand...
- ERA: Entropy-Guided Visual Token Pruning with Rectified Attention for Efficient MLLMs
Multimodal Large Language Models (MLLMs) incur prohibitive inference costs due to long visual token sequences. Training-free visual token reduction provides an efficient solution. However, existing methods distort attention distributions, giving rise to a phenomenon we term Attention Logit Collapse....
- FlexViT: A Flexible FPGA-based Accelerator for Edge Vision Transformers
Deploying Vision Transformer (ViT) models on edge platforms remains challenging due to their high computational demands and the architectural heterogeneity of modern hybrid ViT models, which incorporate both fully connected and convolutional layers. This heterogeneity leads to significant variation ...
- No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs
We introduce VidPair-Halluc, a new benchmark for evaluating video hallucination in large video models (LVMs) under rigorous and controlled conditions. Unlike previous benchmarks that primarily rely on text-based perturbations or adversarial questions while neglecting the consistency of visual backgr...
- DriveWeaver: Point-Conditioned Video Inpainting for Controllable Vehicle Insertion in Autonomous Driving Simulation
A pivotal step in autonomous driving simulation involves inserting foreground vehicles with predefined trajectories into simulated scenes. This process enhances scene diversity and facilitates the creation of various corner cases for testing and improving autonomous driving models. However, existing...
- RESOLVE: A Multi-Resolution and Multi-Modal Dataset for Roadside Cooperative Perception
LiDAR has increasingly been integrated into traffic cameras to expand coverage and mitigate occlusion in roadside cooperative perception. However, how unimodal and camera-LiDAR fusion architectures behave under variations in LiDAR point sparsity induced by sensor configurations and scene-dependent s...
- SENSE-VAD: Sentient and Semantic Video Anomaly Detection for Autonomous Driving
Autonomous vehicles (AVs) must navigate not only motion-based hazards but also socially complex situations whose danger is constituted by inter-agent relationships rather than movement statistics alone. A child running away from a guardian, a person being carried by another, or a pursuer chasing a p...
- Towards Voxel Spacing Consistency for Medical Image Segmentation
Volumetric medical image segmentation is essential for both preoperative diagnosis and intraoperative guidance. While recent years have witnessed rapid progress in segmentation architectures, comparatively little attention is paid to the physical voxel spacing of anatomical data. Indeed, volumetric ...
- PriorEye: Geospatial Visual Priors for End-to-End Autonomous Driving
Most end-to-end autonomous driving methods rely solely on instantaneous sensor observations, limiting them to reactive behavior without the anticipatory foresight human drivers employ through prior experience. We introduce geospatial visual priors, street-level visual context anchored to the intende...
- MuSViT: A Foundation Vision Model for Sheet Music Representation
Foundation models have transformed vision and language processing by providing rich, reusable representations that transfer across diverse tasks. Sheet music, as a visual encoding of musical language, lacks such a strong domain-specific backbone. We introduce MuSViT (Music Score Vision Transformer):...
- UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization
Visual-to-Code generation, which transforms scientific plots, vector graphics, and webpages into executable scripts, demands a level of pixel-precise alignment that standard Multimodal Large Language Models (MLLMs) fail to achieve through Supervised Fine-Tuning (SFT) alone. While Reinforcement Learn...
- Intrinsically Stable Spiking Neural Networks: Overcoming the Performance Barrier in the Absence of Batch Normalization
The performance of deep spiking neural networks (SNNs) often relies on batch normalization (BN). However, the advanced dynamic BN variants used in state-of-the-art models introduce runtime multiplications, which weaken the hardware-efficiency motivation of SNNs. To address this tension, we identify ...
- Semantic Occupancy Prediction with Dual Range-Voxel Representation
LiDAR-based 3D semantic occupancy prediction, which aims to provide accurate and comprehensive scene representation, is crucial for autonomous driving systems. As point clouds suffer from sparsity and incompleteness, leading to insufficient semantic learning and difficult occupancy perception, exist...
- FaceMoE: Mixture of Experts for Low-Resolution Face Recognition
Low-resolution face recognition (LR-FR) remains a challenging task due to poor feature extraction and aggregation, as probe images often contain limited identity information resulting from extreme degradations such as blur, occlusion, and low contrast. Additionally, the domain gap between high-resol...
- GEAR: Guided End-to-End AutoRegression for Image Synthesis
Visual generative models are typically trained in two stages. A tokenizer is first trained for reconstruction and then frozen, after which a generator is trained on its discrete indices or continuous latents. This decoupling leaves the tokenizer unaware of what the generator finds easy to model. We ...
- Ferguson
Is your landing page actually... landing? Ferguson tells you
- PointSplat: Compact Gaussian Splatting via Human-Centric Prediction
Producing 3D human representations from input views on the fly is essential for immersive live streaming systems, where representation compactness is as critical as high fidelity given limited computational power and transmission bandwidth. Although recent feed-forward reconstruction methods achieve...
- Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers
Modern one-step diffusion models achieve impressive quality through distribution-based timestep distillation. Yet, they rely on a critical assumption: Teacher and Student must inhabit the same latent space. This Shared-Space constraint prevents knowledge transfer from modern high-capacity Teachers (...
- Planar-SfM: Camera Pose Estimation via Homography Graph Embeddings
Structure from Motion (SfM) systems traditionally struggle with planar scenes, where standard epipolar geometry-based methods become degenerate. Rather than viewing planar surfaces as a limitation, we propose a unified framework that leverages them as a source of geometric constraints. Our key insig...
- AnyBokeh: Physics-Guided Any-to-Any Bokeh Editing with Optical Fingerprint Transfer
Depth-of-field control is a fundamental tool in photography, yet post-capture bokeh editing from a single image remains challenging. A practical editor should handle images captured under arbitrary focus and aperture settings. Existing methods typically assume an all-in-focus input, or first recover...
- DEMUN: Fast and accurate discovery of music notation in very large collections
Much of written musical heritage is preserved and digitised at memory institutions: libraries, museums, and archives. Owing to their collection structures, sheet music tends to be concentrated in large subsets that are defined as collections of music, with corresponding metadata that makes the music...
- World Narrative Model for Highly Controllable Video Generation: A Paradigm Shift from Pixel Sampling to Physical World Orchestration
The fundamental obstacle to industrial grade video generation is the lack of controllability: existing models treat video as a pixel distribution sampling problem, bypassing the explicit, instance level $4D$ $(3D + T)$ physical world. Consequently, content creators cannot specify geometry, motion, c...
- InstanceControl: Controllable Complex Image Generation without Instance Labeling
Controllable image generation methods, such as ControlNet, have demonstrated a remarkable capacity to introduce visual conditions(e.g., depth maps) to guide image generation. However, these methods often struggle with complex multi-instance scenes, frequently leading to attribute confusion among ins...
- Absorption-Feature-Guided Distance-Decoupled Estimation and Band Selection for LWIR Hyperspectral Passive Ranging
Long-wave infrared (LWIR) hyperspectral observations contain distance-dependent atmospheric absorption signatures, providing a physical basis for long-range passive ranging. However, in natural scenes, these signatures are nonlinearly coupled with target temperature, material emissivity, and path ra...
- Generative Lane Topology Reasoning via Autoregressive Model with Geometry Prior
Lane topology reasoning aims to construct a lane graph from onboard sensor observations. Existing methods follow a detection and association paradigm that treats each lane instance independently, leading to geometric inconsistency at connected endpoints and incomplete graphs due to visual occlusions...