相关论文: Tool-Augmented Hybrid Ensemble Reasoning with Dist…

We present FerKD, a novel efficient knowledge distillation framework that incorporates partial soft-hard label adaptation coupled with a region-calibration mechanism. Our approach stems from the observation and intuition that standard data…

Can post-trained large language models (LLMs) further improve themselves using only unlabeled prompts, without external teachers or feedback from tools? We study this setting starting only from unlabeled seed questions with no ground-truth…

Proof assistants, such as Isabelle/HOL, offer tools to facilitate inductive theorem proving. Isabelle experts know how to use these tools effectively; however, there is a little tool support for transferring this expert knowledge to a wider…

Current research efforts are focused on enhancing the thinking and reasoning capability of large language model (LLM) by prompting, data-driven emergence and inference-time computation. In this study, we consider stimulating language…

Diffusion models excel at generative modeling (e.g., text-to-image) but sampling requires multiple denoising network passes, limiting practicality. Efforts such as progressive distillation or consistency distillation have shown promise by…

Distilling knowledge from large proprietary models (e.g., GPT-4) to tiny deployable models (less than 1B parameters) faces a critical capacity-budget trap: the 1000x capacity gap between teachers and students prevents effective direct…

Tool-integrated reasoning (TIR) offers a direct way to extend thinking models beyond the limits of text-only reasoning. Paradoxically, we observe that tool-enabled evaluation can degrade reasoning performance even when the strong thinking…

Diffusion distillation, exemplified by Distribution Matching Distillation (DMD), has shown great promise in few-step generation but often sacrifices quality for sampling speed. While integrating Reinforcement Learning (RL) into distillation…

Distillation enables compact Vision-Language Models (VLMs) to obtain strong reasoning capabilities, yet the prompts driving this process are typically chosen via simple heuristics or aggregated from off-the-shelf datasets. We reveal a…

Improving the reasoning capabilities of large language models (LLMs) typically relies either on the model's ability to sample a correct solution to be reinforced or on the existence of a stronger model able to solve the problem. However,…

RGB cameras excel at capturing rich texture details with high spatial resolution, whereas event cameras offer exceptional temporal resolution and a high dynamic range (HDR). Leveraging their complementary strengths can substantially enhance…

Hybrid computation combines discrete and continuous dynamics in the form of an entangled mixture inherently present both in various natural phenomena, and in applications ranging from control theory to microbiology. The emergent behaviours…

Large-scale language models have recently demonstrated impressive empirical performance. Nevertheless, the improved results are attained at the price of bigger models, more power consumption, and slower inference, which hinder their…

How to learn highly compact yet effective sentence representation? Pre-trained language models have been effective in many NLP tasks. However, these models are often huge and produce large sentence embeddings. Moreover, there is a big…

This paper explores sequence-level knowledge distillation (KD) of multilingual pre-trained encoder-decoder translation models. We argue that the teacher model's output distribution holds valuable insights for the student, beyond the…

Distilled self-supervised models have shown competitive performance and efficiency in recent years. However, there is a lack of experience in jointly distilling multiple self-supervised speech models. In our work, we performed Ensemble…

Pre-trained models like BERT (Devlin et al., 2018) have dominated NLP / IR applications such as single sentence classification, text pair classification, and question answering. However, deploying these models in real systems is highly…

Hybrid models combining Transformers and State Space Models (SSMs) are promising for balancing performance and efficiency. However, optimizing these hybrid models, particularly by addressing the potential redundancy inherent within the…

Visual language reasoning requires a system to extract text or numbers from information-dense images like charts or plots and perform logical or arithmetic reasoning to arrive at an answer. To tackle this task, existing work relies on…

Large language models trained with reinforcement learning (RL) for mathematical reasoning face a fundamental challenge: on problems the model cannot solve at all - "cliff" prompts - the RL gradient vanishes entirely, preventing any learning…