HuggingFace
CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs
Representing a 3D scene as multi-view images allows 2D VLMs to reason in 3D by reusing priors from pre-training, side...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?
Vision-Language-Action (VLA) models have shown promising progress in language-conditioned robotic manipulation. Howev...
HuggingFace
Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions
Large language models often answer structurally unanswerable questions, such as computing cot(-540°) or evaluating (1...
HuggingFace
ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding
In this paper, we propose ReactVAU, a Slow-Fast Decoupled Framework for real-time streaming Video Anomaly Understandi...
HuggingFace
SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions
Compressing large-scale neural networks is essential for deploying models on resource-constrained devices. Most exist...
HuggingFace
Measuring Language Transfer in Robot Policies: Adding Greek to a Cosmos3 Vision-Language-Action Policy
Robot foundation models are trained and evaluated predominantly in English, and robot demonstration corpora do not ex...
HuggingFace
Cadence: Error-Bounded Lossy Compression of Demand Time Series with a Time-Series Foundation Model
We present Cadence, an error-bounded lossy compressor for numeric time series pairing a 330M-parameter time-series fo...
HuggingFace
Encoded Early, Used Late: Where Transformers Begin to Act on an Inferred Partner's Expertise
A transformer can make an attribute linearly decodable in its residual stream at a depth where that attribute does no...
HuggingFace
Harnessing CLIP and DINO: An Uncertainty-Aware Cascaded Fusion Network for Generalizable Deepfake Image Detection
The growing realism and accessibility of manipulated and generated faces threaten the trustworthiness of digital medi...
HuggingFace
RelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting
Image relighting is traditionally tackled via complex inverse rendering pipelines, which suffer from ill-posed optimi...
HuggingFace
Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation
Monocular depth estimation is a ubiquitous yet highly ill-posed computer vision task, with downstream applications in...
HuggingFace
A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM
Chain-of-Thought (CoT) improves the reasoning ability of Large Language Models (LLMs) but incurs substantial computat...