· ai
[Paper] OneThinker: All-in-one Reasoning Model for Image and Video
Reinforcement learning (RL) has recently achieved remarkable success in eliciting visual reasoning within Multimodal Large Language Models (MLLMs). However, exi...
-
- · ai
[Paper] PPTArena: A Benchmark for Agentic PowerPoint Editing
We introduce PPTArena, a benchmark for PowerPoint editing that measures reliable modifications to real slides under natural-language instructions. In contrast t...
- · ai
[Paper] MultiShotMaster: A Controllable Multi-Shot Video Generation Framework
Current video generation techniques excel at single-shot clips but struggle to produce narrative multi-shot videos, which require flexible shot arrangement, coh...
- · ai
[Paper] Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation
We investigate whether video generative models can exhibit visuospatial intelligence, a capability central to human cognition, using only visual data. To this e...
- · ai
[Paper] ViSAudio: End-to-End Video-Driven Binaural Spatial Audio Generation
Despite progress in video-to-audio generation, the field focuses predominantly on mono output, lacking spatial immersion. Existing binaural approaches remain co...
- · ai
[Paper] Learning Physically Consistent Lagrangian Control Models Without Acceleration Measurements
This article investigates the modeling and control of Lagrangian systems involving non-conservative forces using a hybrid method that does not require accelerat...
- · ai
[Paper] MAViD: A Multimodal Framework for Audio-Visual Dialogue Understanding and Generation
We propose MAViD, a novel Multimodal framework for Audio-Visual Dialogue understanding and generation. Existing approaches primarily focus on non-interactive sy...
- · ai
[Paper] SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control
Data-driven motion priors that can guide agents toward producing naturalistic behaviors play a pivotal role in creating life-like virtual characters. Adversaria...
- · ai
[Paper] The Moral Consistency Pipeline: Continuous Ethical Evaluation for Large Language Models
The rapid advancement and adaptability of Large Language Models (LLMs) highlight the need for moral consistency, the capacity to maintain ethically coherent rea...
- · ai
[Paper] LORE: A Large Generative Model for Search Relevance
Achievement. We introduce LORE, a systematic framework for Large Generative Model-based relevance in e-commerce search. Deployed and iterated over three years, ...
- · ai
[Paper] TokenPowerBench: Benchmarking the Power Consumption of LLM Inference
Large language model (LLM) services now answer billions of queries per day, and industry reports show that inference, not training, accounts for more than 90% o...
- · ai
[Paper] Unrolled Networks are Conditional Probability Flows in MRI Reconstruction
Magnetic Resonance Imaging (MRI) offers excellent soft-tissue contrast without ionizing radiation, but its long acquisition time limits clinical utility. Recent...