English
Related papers

Related papers: Reward-Aware Trajectory Shaping for Few-step Visua…

200 papers

We consider joint trajectory generation and tracking control for under-actuated robotic systems. A common solution is to use a layered control architecture, where the top layer uses a simplified model of system dynamics for trajectory…

Robotics · Computer Science 2023-07-27 Anusha Srikanthan , Fengjun Yang , Igor Spasojevic , Dinesh Thakur , Vijay Kumar , Nikolai Matni

Reinforcement learning (RL) has been effective for post-training autoregressive (AR) language models, but extending these methods to diffusion language models (DLMs) is challenging due to intractable sequence-level likelihoods. Existing…

Recently, one-stage trackers that use a joint model to predict both detections and appearance embeddings in one forward pass received much attention and achieved state-of-the-art results on the Multi-Object Tracking (MOT) benchmarks.…

Computer Vision and Pattern Recognition · Computer Science 2022-05-12 Shuzhi Yu , Guanhang Wu , Chunhui Gu , Mohammed E. Fathy

Knowledge distillation (KD) which transfers the knowledge from a large teacher model to a small student model, has been widely used to compress the BERT model recently. Besides the supervision in the output in the original KD, recent works…

Computation and Language · Computer Science 2020-12-14 Xiaoqi Jiao , Huating Chang , Yichun Yin , Lifeng Shang , Xin Jiang , Xiao Chen , Linlin Li , Fang Wang , Qun Liu

Process reward models (PRMs) that provide dense, step-level feedback have shown promise for reinforcement learning, yet their adoption remains limited by the need for expensive step-level annotations or ground truth references. We propose…

Machine Learning · Computer Science 2025-12-04 Salman Rahman , Sruthi Gorantla , Arpit Gupta , Swastik Roy , Nanyun Peng , Yang Liu

Teaching agents to follow complex written instructions has been an important yet elusive goal. One technique for enhancing learning efficiency is language reward shaping (LRS). Within a reinforcement learning (RL) framework, LRS involves…

Artificial Intelligence · Computer Science 2023-08-21 Sukai Huang , Nir Lipovetzky , Trevor Cohn

The incorporation of online reinforcement learning (RL) into diffusion and flow-based generative models has recently gained attention as a powerful paradigm for aligning model behavior with human preferences. By leveraging stochastic…

Machine Learning · Computer Science 2025-11-25 Yujie Zhou , Pengyang Ling , Jiazi Bu , Yibin Wang , Yuhang Zang , Jiaqi Wang , Li Niu , Guangtao Zhai

Knowledge distillation is an efficient strategy to use data generated by large "teacher" language models to train smaller capable "student" models, but selecting the optimal teacher for a specific student-task combination requires expensive…

Machine Learning · Computer Science 2025-12-23 Abhishek Panigrahi , Bingbin Liu , Sadhika Malladi , Sham Kakade , Surbhi Goel

Potential-based reward shaping (PBRS) is a particular category of machine learning methods which aims to improve the learning speed of a reinforcement learning agent by extracting and utilizing extra knowledge while performing a task. There…

Artificial Intelligence · Computer Science 2023-03-15 Babak Badnava , Mona Esmaeili , Nasser Mozayani , Payman Zarkesh-Ha

Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a…

Computer Vision and Pattern Recognition · Computer Science 2020-06-24 Ruoyu Sun , Fuhui Tang , Xiaopeng Zhang , Hongkai Xiong , Qi Tian

Transformers trained via Reinforcement Learning (RL) with outcome-based supervision can spontaneously develop the ability to generate intermediate reasoning steps (Chain-of-Thought). Yet the mechanism by which sparse rewards drive policy…

Machine Learning · Computer Science 2026-02-03 Yuval Ran-Milo , Yotam Alexander , Shahar Mendel , Nadav Cohen

Reward-based fine-tuning steers a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model. Although existing methods are derived from different perspectives, we show…

Machine Learning · Computer Science 2026-05-08 Jeongjae Lee , Jinho Chang , Jeongsol Kim , Jong Chul Ye

Layer-wise distillation is a powerful tool to compress large models (i.e. teacher models) into small ones (i.e., student models). The student distills knowledge from the teacher by mimicking the hidden representations of the teacher at…

Computation and Language · Computer Science 2023-06-07 Chen Liang , Simiao Zuo , Qingru Zhang , Pengcheng He , Weizhu Chen , Tuo Zhao

Toddlers evolve from free exploration with sparse feedback to exploiting prior experiences for goal-directed learning with denser rewards. Drawing inspiration from this Toddler-Inspired Reward Transition, we set out to explore the…

Machine Learning · Computer Science 2024-03-19 Junseok Park , Yoonsung Kim , Hee Bin Yoo , Min Whoo Lee , Kibeom Kim , Won-Seok Choi , Minsu Lee , Byoung-Tak Zhang

Large reasoning models achieve strong performance on complex tasks through long chain-of-thought (CoT) trajectories, but directly transferring such reasoning processes to smaller models remains challenging. A key difficulty is that not all…

Computation and Language · Computer Science 2026-04-06 Chaoqun He , Yingfa Chen , Chaojun Xiao , Xu Han , Lijie Wen

Deep Reinforcement Learning is a promising tool for robotic control, yet practical application is often hindered by the difficulty of designing effective reward functions. Real-world tasks typically require optimizing multiple objectives…

Machine Learning · Computer Science 2026-03-06 Kilian Freitag , Knut Åkesson , Morteza Haghir Chehreghani

Information-seeking is a core capability for AI agents, requiring them to gather and reason over tool-generated information across long trajectories. However, such multi-step information-seeking tasks remain challenging for agents backed by…

Artificial Intelligence · Computer Science 2025-11-25 Jaewoo Lee , Archiki Prasad , Justin Chih-Yao Chen , Zaid Khan , Elias Stengel-Eskin , Mohit Bansal

Text-to-image diffusion models often memorize training data, revealing a fundamental failure to generalize beyond the training set. Current mitigation strategies typically sacrifice image quality or prompt alignment to reduce memorization.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Sathwik Karnik , Juyeop Kim , Sanmi Koyejo , Jong-Seok Lee , Somil Bansal

By formulating data samples' formation as a Markov denoising process, diffusion models achieve state-of-the-art performances in a collection of tasks. Recently, many variants of diffusion models have been proposed to enable controlled…

Machine Learning · Computer Science 2023-04-17 Hengtong Zhang , Tingyang Xu

Diffusion models have emerged as a powerful paradigm for generative sequential recommendation, which typically generate next items to recommend guided by user interaction histories with a multi-step denoising process. However, the…

Information Retrieval · Computer Science 2025-10-23 Wenyu Mao , Jiancan Wu , Guoqing Hu , Zhengyi Yang , Wei Ji , Xiang Wang