Related papers: RePIC: Reinforced Post-Training for Personalizing …
Despite the success of large language models (LLMs) in various natural language processing (NLP) tasks, the stored knowledge in these models may inevitably be incomplete, out-of-date, or incorrect. This motivates the need to utilize…
Advanced reasoning in LLMs on challenging domains like mathematical reasoning can be tackled using verifiable rewards based reinforced fine-tuning (ReFT). In standard ReFT frameworks, a behavior model generates multiple completions with…
Reinforcement fine-tuning (RFT) often suffers from reward over-optimization, where a policy model hacks the reward signals to achieve high scores while producing low-quality outputs. Our theoretical analysis shows that the key lies in…
Facilitated by large language models (LLMs), personalized text generation has become a rapidly growing research direction. Most existing studies focus on designing specialized models for a particular domain, or they require fine-tuning the…
Recent advancements in Contrastive Language-Image Pre-training (CLIP) have demonstrated notable success in self-supervised representation learning across various tasks. However, the existing CLIP-like approaches often demand extensive GPU…
Given a textual description, the task of referring expression comprehension (REC) involves the localisation of the referred object in an image. Multimodal large language models (MLLMs) have achieved high accuracy on REC benchmarks through…
Reinforcement learning (RL) has become a key technique for enhancing the reasoning abilities of large language models (LLMs), with policy-gradient algorithms dominating the post-training stage because of their efficiency and effectiveness.…
While image generation techniques are now capable of producing high-quality images that respect prompts which span multiple sentences, the task of text-guided image editing remains a challenge. Even edit requests that consist of only a few…
Post-training of large language models routinely interleaves supervised fine-tuning (SFT) with reinforcement learning (RL). These two methods have different objectives: SFT minimizes the cross-entropy loss between model outputs and expert…
Reinforcement Learning (RL) benefits Large Language Models (LLMs) for complex reasoning. Inspired by this, we explore integrating spatio-temporal specific rewards into Multimodal Large Language Models (MLLMs) to address the unique…
Vision-Language Models (VLMs) demonstrate remarkable general-purpose capabilities but often fall short in specialized domains such as medical imaging or geometric problem-solving. Supervised Fine-Tuning (SFT) can enhance performance within…
Recently it has shown that the policy-gradient methods for reinforcement learning have been utilized to train deep end-to-end systems on natural language processing tasks. What's more, with the complexity of understanding image content and…
Recent work on applying large language models (LMs) achieves impressive performance in many NLP applications. Adapting or posttraining an LM using an unlabeled domain corpus can produce even better performance for end-tasks in the domain.…
Data contamination poses a significant threat to the reliable evaluation of Large Language Models (LLMs). This issue arises when benchmark samples may inadvertently appear in training sets, compromising the validity of reported performance.…
Large Language Models (LLMs) have made substantial strides in structured tasks through Reinforcement Learning (RL), demonstrating proficiency in mathematical reasoning and code generation. However, applying RL in broader domains like…
The development of Large Language Models (LLMs) often confronts challenges stemming from the heavy reliance on human annotators in the reinforcement learning with human feedback (RLHF) framework, or the frequent and costly external queries…
Visual-language pre-training has achieved remarkable success in many multi-modal tasks, largely attributed to the availability of large-scale image-text datasets. In this work, we demonstrate that Multi-modal Large Language Models (MLLMs)…
Video-text retrieval has been stuck in the information mismatch caused by personalized and inadequate textual descriptions of videos. The substantial information gap between the two modalities hinders an effective cross-modal representation…
With the rise of LLMs, there is an increasing need for intelligent recommendation assistants that can handle complex queries and provide personalized, reasoning-driven recommendations. LLM-based recommenders show potential but face…
Debates about large language model post-training often treat supervised fine-tuning (SFT) as imitation and reinforcement learning (RL) as discovery. But this distinction is too coarse. What matters is whether a training procedure increases…