Perceptual Flow Matching for Few-Step Generative Modeling
We propose Perceptual Flow Matching (PFM), a simple yet effective framework for few-step generation in flow-matching models. Rather than performing velocity regression in the conve...
Papers
Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model
Recent progress in large-scale generative models has substantially advanced video generation, yet existing methods remain constrained by a rigid inference paradigm. Bidirectional d...
Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning
Dense video captioning aims to generate temporally grounded descriptions of video events, benefiting both event-level video understanding and generation. In this domain, autoregres...
SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe
While skill optimization for autonomous agents has gained traction, existing methods rely on complex pipelines. This leaves a fundamental question unaddressed: What constitutes a m...
VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speech
Large Audio-Language Models (LALMs) are increasingly integrated into daily applications, yet their generative biases remain underexplored. Existing speech fairness benchmarks rely ...
Automating the Design of Embodied Agent Architectures
Embodied agents are typically built as hand-designed compositions of perception, memory, planning, and action modules. This modularity exposes a large architectural design space, b...
Bibby AI: An Editor-Native Agentic Platform for Academic Research, Writing, and Publishing
Academic output is produced across a fragmented toolchain: literature discovery in one application, reference management in another, writing in a LaTeX editor, formatting against v...
Layer-wise Cross-Lingual Depression Detection from Speech: Analysis with Contrastive Alignment
Significant disparities exist in the diagnosis and clinical presentation of depression across different linguistic populations. Speech-based depression detection performs well mono...
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
Scaling modern large language models (LLMs) to long contexts is limited by the quadratic computation cost, and poor length extrapolation of dense attention. Chunk-wise sparse atten...
Speaker-Aware Temporal Aggregation Strategies on Segment Representations for Depression Detection in Dyadic Interaction: A Benchmark Study
Speech-based depression detection compresses features from short audio segments into one speaker-level decision, a step called temporal aggregation rarely studied on its own. Most ...
PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction
Long-horizon behavior prediction aims to infer a user's next action based on a lengthy historical sequence, playing a crucial role in artificial intelligence field. The rise of lar...
Taste-aware music retrieval from audio embeddings
Crossmodal correspondences between sound and taste are well established in psychology and neuroscience, but largely absent from content-based multimedia retrieval. We formalise tas...
MentalThink: Shaping Thoughts in Mental SVG World
We introduce MentalThink, a visual-symbolic reasoning paradigm that equips Multimodal LLMs (MLLMs) with an executable mechanism for "mental" visualization. The core of MentalThink ...
Program-as-Weights: A Programming Paradigm for Fuzzy Functions
Many everyday programming tasks resist clean rule-based implementation, such as alerting on important log lines, repairing malformed JSON, or ranking search results by intent, and ...
Optimizing Visual Generative Models via Distribution-wise Rewards
Conventional reinforcement learning strategies for visual generation typically employ sample-wise reward functions, yet this practice frequently results in reward hacking that degr...
AgenticDataBench: A Comprehensive Benchmark for Data Agents
Data science aims to derive actionable insights from heterogeneous raw data, unlocking the value of the massive amounts of data generated in modern society. Automating this process...
WARP: Weight-Space Analysis for Recovering Training Data Portfolios
Foundation models are routinely released to the public, yet the data recipes used to train them -- such as domain mixture weights that determine how different sources are sampled -...
Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots
Embodied AI models now span vision-language-action (VLA) models and world-action models (WAMs), but practical deployment remains fragmented across model-specific Python stacks, bac...
Rank-Then-Act: Reward-Free Control from Frame-Order Progress
We introduce Rank-Then-Act (RTA), a framework for learning control policies from expert video demonstrations without environment rewards. RTA trains a Vision-Language Model (VLM) o...
EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
Autonomous agents are increasingly expected to improve executable policies through feedback, yet existing evaluations often collapse this process into a final score or confound it ...
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
State-of-the-art single-image 3D reconstruction methods often rely on complex hybrid architectures and loss functions, or compress geometry into latent spaces in order to leverage ...
Video-Oasis: Rethinking Evaluation of Video Understanding
The inherent complexity of video understanding makes it difficult to determine whether Video-LLM benchmark performance stems from visual perception, linguistic reasoning, or knowle...
VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon
Vision-Language-Action (VLA) foundation models have recently achieved strong progress in embodied intelligence. To reduce policy-call frequency while preserving temporal coherence,...
Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training
Reinforcement learning (RL) has become a central component of post-training large language models (LLMs), yet little is understood about how RL adaptation is distributed across tra...