13 papers
On-Policy Residual Learning for Diffusion Language Models
Yifan Yu, Yuqing Jian, Jisen Li +9
Residual context is key to unlocking the speed-quality Pareto frontier of diffusion language models (DLMs) by carrying forward predictive distributions across denoising steps. Yet…
QATFactory: A Versatile, Deployment-Aligned Framework for Quantization-aware Training and Distillation of LLMs
Weili Xu, Jisen Li, Yuqing Jian +8
Large language model (LLM) inference is increasingly moving toward lower precision to realize the throughput of hardware accelerators, but aggressive post-training quantization (PT…
Tail-Likelihood Reinforcement Learning
Shrinivas Ramasubramanian, Daman Arora, Fahim Tajwar +11
Reinforcement learning typically optimizes average reward. For generative policies, the average can hide an important distinction: two policies can achieve the same mean reward whi…
Osprey: Target-agnostic Pre-training Makes Stronger Drafters in Speculative Decoding
Fengxiang Bie, Yuqing Jian, Yifan Yu +7
Speculative decoding is critical for accelerating LLM inference. However, the speedup is fragile: drafters are typically trained against a narrow distribution for a single target m…
ThunderAgent: A Simple, Fast and Program-Aware Agentic Inference System
Hao Kang, Ziyang Li, Weili Xu +7
Large language models(LLMs) are now used to power complex multi-turn agentic workflows. Existing systems run agentic inference by loosely assembling isolated components: an LLM inf…
When RL Meets Adaptive Speculative Training: A Unified Training-Serving System
Junxiong Wang, Fengxiang Bie, Jisen Li +14
Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentangle speculator training from serving, treating speculator training as a standalone…
OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learning
Guanhua Ji, Harsha Polavaram, Lawrence Yunliang Chen +5
Large and diverse datasets are needed for training generalist robot policies that have potential to control a variety of robot embodiments -- robot arm and gripper combinations --…
Beat the long tail: Distribution-Aware Speculative Decoding for RL Training
Zelei Shao, Vikranth Srivatsa, Sanjana Srivastava +12
Reinforcement learning(RL) post-training has become essential for aligning large language models (LLMs), yet its efficiency is increasingly constrained by the rollout phase, where…
CaptionQA: Is Your Caption as Useful as the Image Itself?
Shijia Yang, Yunong Liu, Bohan Zhai +5
Image captions serve as efficient surrogates for visual content in multimodal systems such as retrieval, recommendation, and multi-step agentic inference pipelines. Yet current eva…
CDLM: Consistency Diffusion Language Models For Faster Sampling
Minseo Kim, Chenfeng Xu, Coleman Hooper +5
Diffusion Language Models (DLMs) offer a promising parallel generation paradigm but suffer from slow inference due to numerous refinement steps and the inability to use standard KV…
LDGNet: A Lightweight Difference Guiding Network for Remote Sensing Change Detection
Chenfeng Xu
With the rapid advancement of deep learning, the field of change detection (CD) in remote sensing imagery has achieved remarkable progress. Existing change detection methods primar…
FlowKV: A Disaggregated Inference Framework with Low-Latency KV Cache Transfer and Load-Aware Scheduling
Weiqing Li, Guochao Jiang, Xiangyong Ding +5
Disaggregated inference has become an essential framework that separates the prefill (P) and decode (D) stages in large language model inference to improve throughput. However, the…
CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Prediction
Zhangchen Ye, Tao Jiang, Chenfeng Xu +2
Vision-based 3D occupancy prediction is significantly challenged by the inherent limitations of monocular vision in depth estimation. This paper introduces CVT-Occ, a novel approac…