HuggingFace
Trace: A Taxonomy-Guided Environment for Multidomain Visual Reasoning
Reinforcement learning with verifiable rewards (RLVR) has substantially improved language-model reasoning, yet its ex...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
FVAttn: Adaptive Sparse Attention with Runtime Load Balancing for Video Generation
Video Diffusion Transformers process long spatio-temporal sequences, making self-attention the main bottleneck in hig...
HuggingFace
Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations
Natural-language autoencoders score explanations of hidden activations by reconstruction: an explanation is deemed fa...
HuggingFace
An Exam for Active Observers
Human vision is a closed loop: gaze is continuously redirected by intermediate hypotheses rather than a single snapsh...
HuggingFace
Scaling Laws for Hypernetwork-Based Knowledge Injection in Large Language Models
Injecting factual knowledge into large language models (LLMs) reliably and at scale remains an open challenge. Hypern...
HuggingFace
DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations
As autonomous agents rapidly evolve, their ability to reliably manipulate ubiquitous digital documents has become cri...
HuggingFace
Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing
Modern ASR models trained on heterogeneously annotated data treat transcription style (verbatim vs. intended) as an u...
HuggingFace
Subliminal Clocks: Latent Time Modelling in Diffusion Language Models
Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive models. Unlike st...
HuggingFace
AutoIndex: Learning Representation Programs for Retrieval
We present AutoIndex, a framework for learning representation programs: executable transformations that map raw docum...
arXiv
GUIDED Network-Agnostic Feature Initialization for Spatial Transferability in GNN-based Models
The Traffic Assignment Problem is a fundamental but computationally expensive component of transportation planning. W...
arXiv
The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems
Current AI safety discourse still focuses disproportionately on visible failures, including obvious harms, dramatic m...
arXiv
Graph-Based Agentic AI with LangGraph: Workflow Pathways for Long-Running Stateful Business Processes
This paper is a practitioner guide to graph-based workflow pathways for long-running, stateful, multi-step generative...