11 papers
Arachne: Orchestrating Cascades for Efficient Text-to-Video Model Training
Peng Yu, Yuankai Fan, Yang Qiu +4
The rising demand for AI-generated videos is fueled by advances in large-scale Text-to-Video (T2V) models, trained on extensive datasets of video clips spanning diverse resolutions…
GN0: Toward a Unified Paradigm for Generation, Evaluation, and Policy Learning in Visual-Language Navigation
Xinhai Li, Xiaotao Zhang, Yuehao Huang +10
Embodied navigation connects intelligent agents with the physical world and is fundamental for general robotic intelligence. Limited availability and quality of navigation data hav…
PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations
Yang Zhang, Jiangyuan Zhao, Chenyou Fan +11
Vision-Language-Action (VLA) models advance robotic control via strong visual-linguistic priors. However, existing VLAs predominantly frame pretraining as supervised behavior cloni…
Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression
Ruoling Qi, Yirui Liu, Xuaner Wu +6
The deployment of Large Language Models is constrained by the memory and bandwidth demands of static weights and dynamic Key-Value cache. SVD-based compression provides a hardware-…
Tele-Omni: a Unified Multimodal Framework for Video Generation and Editing
Jialun Liu, Tian Li, Xiao Cao +20
Recent advances in diffusion-based video generation have substantially improved visual fidelity and temporal coherence. However, most existing approaches remain task-specific and r…
TeleBoost: A Systematic Alignment Framework for High-Fidelity, Controllable, and Robust Video Generation
Yuanzhi Liang, Xuan'er Wu, Yirui Liu +12
Post-training is the decisive step for converting a pretrained video generator into a production-oriented model that is instruction-following, controllable, and robust over long te…
KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs
Jian Chen, Zhuoran Wang, Jiayu Qin +6
Large language models rely on kv-caches to avoid redundant computation during autoregressive decoding, but as context length grows, reading and writing the cache can quickly satura…
Beyond Binary: Turning Partial Success into Dense Verifiable Rewards for Reinforcement Learning in Code Generation
Longwen Wang, Yirui Liu, Xuan'er Wu +6
Effective reward design is a central challenge in Reinforcement Learning (RL) for code generation. Mainstream test-suite-level outcome rewards enforce functional correctness but in…
TeleWorld: Towards Dynamic Multimodal Synthesis with a 4D World Model
Yabo Chen, Yuanzhi Liang, Jiepeng Wang +24
World models aim to endow AI systems with the ability to represent, generate, and interact with dynamic environments in a coherent and temporally consistent manner. While recent vi…
Computation-Bandwidth-Memory Trade-offs: A Unified Paradigm for AI Infrastructure
Yuankai Fan, Qizhen Weng, Xuelong Li
Large-scale artificial intelligence models are transforming industries and redefining human machine collaboration. However, continued scaling exposes critical limitations in hardwa…
Janus: Disaggregating Attention and Experts for Scalable MoE Inference
Zhexiang Zhang, Ye Wang, Yumiao Zhao +9
Serving large Mixture-of-Experts (MoE) models is challenging because of their large memory footprints, heterogeneous resource demands, and highly dynamic inference workloads. Most…