arXiv
Persian Pixel: A large-scale synthetic OCR dataset for Persian language
Optical Character Recognition (OCR) for Persian remains substantially less mature than for Latin-script languages des...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
SoftReason: A Fully Differentiable Neuro-Soft-Symbolic Deductive Reasoning Architecture over High-Dimensional Perceptual Data
In many reasoning problems, the premises are not observed as discrete symbols, but must be inferred from high-dimensi...
HuggingFace
Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model
Large language models can answer scientific questions, yet a correct output does not reveal whether the model represe...
HuggingFace
ATSplat: Compact Feed-forward 3D Gaussian Splatting with Adaptive Token Expansion
3D Gaussian Splatting (3DGS) achieves high-quality novel-view synthesis by optimizing freely placed primitives in 3D ...
HuggingFace
SeededGrasp: Language-Guided Grasping in Complex Scenes with Multiple Embodiments
Practical robotic grasping in complex scenes requires both 3D spatial reasoning and alignment with task-specific requ...
HuggingFace
G-MAD: A Game-Based Data Generation Framework for Multi-View RGB-T Aerial Object Detection
This work introduces G-MAD, an open-source framework that uses Arma3 to generate synchronized multi-view RGB-T data f...
HuggingFace
SLPO: Scaling Latent Reasoning via a Surrogate Policy
Reinforcement learning with verifiable rewards has become the predominant recipe for eliciting test-time scaling in e...
HuggingFace
SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD
Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges fo...
HuggingFace
Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking
As large language models and AI agents become the primary consumers of search results, document set quality determine...
HuggingFace
Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment
Finetuning a pretrained vision-language model (VLM) on robot demonstrations via behavior cloning (BC) has become the ...
HuggingFace
Self Gradient Forcing: Native Long Video Extrapolation
Recent autoregressive video diffusion methods are increasingly built upon Self Forcing, where the student is trained ...
HuggingFace
Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization
Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. However, RL al...