Related papers: HINT-SD: Targeted Hindsight Self-Distillation for …
As Large Language Models (LLMs) scale up, inference efficiency becomes a critical bottleneck. Multi-Token Prediction (MTP) could accelerate LLM inference by predicting multiple future tokens in parallel. However, existing MTP approaches…
Recent advances in few-step diffusion distillation have enabled efficient image generation, yet aligning these models with human preferences remains challenging. We propose Reward-Tilted Distribution Matching Distillation (RTDMD), a…
Hierarchical reinforcement learning (HRL) provides a promising solution for complex tasks with sparse rewards of intelligent agents, which uses a hierarchical framework that divides tasks into subgoals and completes them sequentially.…
We propose a deep learning-based channel estimation, quantization, feedback, and precoding method for downlink multiuser multiple-input and multiple-output systems. In the proposed system, channel estimation and quantization for limited…
Deep learning has shown promise in enhancing channel state information (CSI) feedback. However, many studies indicate that better feedback performance often accompanies higher computational complexity. Pursuing better performance-complexity…
Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignment over long, temporally grounded reasoning trajectories. While reinforcement learning with…
Most deep metric learning (DML) methods employ a strategy that forces all positive samples to be close in the embedding space while keeping them away from negative ones. However, such a strategy ignores the internal relationships of…
Reinforcement Learning (RL) algorithms can suffer from poor sample efficiency when rewards are delayed and sparse. We introduce a solution that enables agents to learn temporally extended actions at multiple levels of abstraction in a…
The advent of scalable deep models and large datasets has improved the performance of Neural Machine Translation. Knowledge Distillation (KD) enhances efficiency by transferring knowledge from a teacher model to a more compact student…
While Reinforcement Learning from Human Feedback (RLHF) has shown promise in aligning generative AI, we present empirical evidence that it can also cause severe, systematic misalignment. We hypothesize that this stems from evaluator…
Optimizing a deep neural network is a fundamental task in computer vision, yet direct training methods often suffer from over-fitting. Teacher-student optimization aims at providing complementary cues from a model trained previously, but…
Knowledge distillation is classically a procedure where a neural network is trained on the output of another network along with the original targets in order to transfer knowledge between the architectures. The special case of…
While deep reinforcement learning methods have shown impressive results in robot learning, their sample inefficiency makes the learning of complex, long-horizon behaviors with real robot systems infeasible. To mitigate this issue,…
Supervised fine-tuning (SFT) is widely used to inject new knowledge into language models, but it often degrades pretrained capabilities such as reasoning and general-domain performance. We argue this forgetting arises because fine-tuning…
Standard Latent Diffusion Models rely on a complex, three-part architecture consisting of a separate encoder, decoder, and diffusion network, which are trained in multiple stages. This modular design is computationally inefficient, leads to…
We present a novel approach to knowledge transfer in model-based reinforcement learning, addressing the critical challenge of deploying large world models in resource-constrained environments. Our method efficiently distills a high-capacity…
Distilling vision-language models into faster hybrid architectures, such as 3:1 Mamba-2/attention mixes, is now standard practice for making inference efficient. Aggregate benchmarks suggest that this works but they hide selective failures.…
Episodic self-imitation learning, a novel self-imitation algorithm with a trajectory selection module and an adaptive loss function, is proposed to speed up reinforcement learning. Compared to the original self-imitation learning algorithm,…
Lifelong imitation learning for manipulation tasks poses significant challenges due to distribution shifts that occur in incremental learning steps. Existing methods often focus on unsupervised skill discovery to construct an ever-growing…
As deep vision models grow increasingly complex to achieve higher performance, deployment efficiency has become a critical concern. Knowledge distillation (KD) mitigates this issue by transferring knowledge from large teacher models to…