Related papers: UniSD: Towards a Unified Self-Distillation Framewo…

The advancement of knowledge distillation has played a crucial role in enabling the transfer of knowledge from larger teacher models to smaller and more efficient student models, and is particularly beneficial for online and…

Large Language Models (LLMs) have displayed remarkable performances across various complex tasks by leveraging Chain-of-Thought (CoT) prompting. Recently, studies have proposed a Knowledge Distillation (KD) approach, reasoning distillation,…

While Unified Multimodal Models (UMMs) have achieved remarkable success in cross-modal comprehension, a significant gap persists in their ability to leverage such internal knowledge for high-quality generation. We formalize this discrepancy…

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…

Knowledge Distillation (KD) is one of the approaches to reduce the size of Large Language Models (LLMs). A LLM with smaller number of model parameters (student) is trained to mimic the performance of a LLM of a larger size (teacher model)…

This paper proposes the DistillCSE framework, which performs contrastive learning under the self-training paradigm with knowledge distillation. The potential advantage of DistillCSE is its self-enhancing feature: using a base model to…

We introduce a novel approach to large language model (LLM) distillation by formulating it as a constrained reinforcement learning problem. While recent work has begun exploring the integration of task-specific rewards into distillation…

Self-supervised speech pre-training enables deep neural network models to capture meaningful and disentangled factors from raw waveform signals. The learned universal speech representations can then be used across numerous downstream tasks.…

Recent works have shown that optical flow can be learned by deep networks from unlabelled image pairs based on brightness constancy assumption and smoothness prior. Current approaches additionally impose an augmentation regularization term…

Diffusion large language models (DLLMs) have emerged as powerful generative models with the promise of fast text generation through parallel decoding. However, realizing this potential in practice remains challenging: reducing the number of…

Teachers' growth mindset supportive language (GMSL)--rhetoric emphasizing that one's skills can be improved over time--has been shown to significantly reduce disparities in academic achievement and enhance students' learning outcomes.…

Large Language Models (LLMs) have showcased exceptional capabilities in various domains, attracting significant interest from both academia and industry. Despite their impressive performance, the substantial size and computational demands…

We present DistillFlow, a knowledge distillation approach to learning optical flow. DistillFlow trains multiple teacher models and a student model, where challenging transformations are applied to the input of the student model to generate…

We study {on-policy self-distillation} (OPSD), where a language model improves its reasoning ability by distilling privileged teacher distributions along its own on-policy trajectories. Despite the performance gains of OPSD, we identify a…

Large language models present challenges for principled uncertainty quantification, in part due to their complexity and the diversity of their outputs. Semantic dispersion, or the variance in the meaning of sampled answers, has been…

On-policy self-distillation has become a strong recipe for LLM reasoning, where a privileged teacher supervises the student's own rollouts while conditioning on the reference solution. A design choice shared by nearly all such methods,…

Federated learning (FL) enables multiple clients to collaboratively train a global model while keeping local data decentralized. Data heterogeneity (non-IID) across clients has imposed significant challenges to FL, which makes local models…

Knowledge distillation (KD) is a promising solution to compress large language models (LLMs) by transferring their knowledge to smaller models. During this process, white-box KD methods usually minimize the distance between the output…

Self-Distillation is a special type of knowledge distillation where the student model has the same architecture as the teacher model. Despite using the same architecture and the same training data, self-distillation has been empirically…

Representation learning has been evolving from traditional supervised training to Contrastive Learning (CL) and Masked Image Modeling (MIM). Previous works have demonstrated their pros and cons in specific scenarios, i.e., CL and supervised…