Related papers: PromptCD: Test-Time Behavior Enhancement via Polar…
Aligning with personalized preferences, which vary significantly across cultural, educational, and political differences, poses a significant challenge due to the computational costs and data demands of traditional alignment methods. In…
Large language models (LLMs) are trained on huge amounts of textual data, and concerns have been raised that the limits of such data may soon be reached. A potential solution is to train on synthetic data sampled from LLMs. In this work, we…
Autoregressive Large Language Models (LLMs) have achieved impressive performance in language tasks but face two significant bottlenecks: (1) quadratic complexity in the attention module as the number of tokens increases, and (2) limited…
Recently, contrastive learning has been shown to be effective in improving pre-trained language models (PLM) to derive high-quality sentence representations. It aims to pull close positive examples to enhance the alignment while push apart…
Alignment with human preference prevents large language models (LLMs) from generating misleading or toxic content while requiring high-cost human feedback. Assuming resources of human annotation are limited, there are two different ways of…
Prompt-Tuning is an efficient method for adapting pre-trained language models to new tasks with minimal computational overhead by modifying prompt embeddings. In this work, we investigate how crucial the phenomenon of embedding collapse,…
We propose Consistency-guided Prompt learning (CoPrompt), a new fine-tuning method for vision-language models. Our approach improves the generalization of large foundation models when fine-tuned on downstream tasks in a few-shot setting.…
Leveraging pre-trained 2D image representations in behavior cloning policies has achieved great success and has become a standard approach for robotic manipulation. However, such representations fail to capture the 3D spatial information…
Contrastive decoding strategies are widely used to reduce object hallucinations in multimodal large language models (MLLMs). These methods work by constructing contrastive samples to induce hallucinations and then suppressing them in the…
Animal pose estimation is challenging for existing image-based methods because of limited training data and large intra- and inter-species variances. Motivated by the progress of visual-language research, we propose that pre-trained…
While Contrastive Decoding (CD) has proven effective at enhancing Large Audio Language Models (LALMs), the underlying mechanisms driving its success and the comparative efficacy of different strategies remain unclear. This study…
The broad capabilities of Language Models (LMs) can be limited by their sensitivity to distractor tasks: LMs can infer secondary tasks from the prompt in addition to the intended one, leading to unwanted outputs. For example, prompt…
As the use of large language models (LLMs) increases within society, as does the risk of their misuse. Appropriate safeguards must be in place to ensure LLM outputs uphold the ethical standards of society, highlighting the positive role…
In robot task planning, large language models (LLMs) have shown significant promise in generating complex and long-horizon action sequences. However, it is observed that LLMs often produce responses that sound plausible but are not…
Large vision-language models (LVLMs) have shown remarkable capabilities in visual-language understanding for downstream multi-modal tasks. Despite their success, LVLMs still suffer from generating hallucinations in complex generation tasks,…
Aligning large language models (LLMs) with human expectations without human-annotated preference data is an important problem. In this paper, we propose a method to evaluate the response preference by using the output probabilities of…
Large language models (LLMs) have shown remarkable capabilities in code generation. However, the effects of hallucinations (e.g., output noise) make it particularly challenging for LLMs to generate high-quality code in one pass. In this…
Vision-language models (VLMs) such as CLIP exhibit strong zero-shot generalization but remain sensitive to domain shifts at test time. Test-time prompt tuning (TPT) mitigates this issue by adapting prompts with fixed augmentations, which…
While Large Vision-Language Models (LVLMs) have rapidly advanced in recent years, the prevalent issue known as the `hallucination' problem has emerged as a significant bottleneck, hindering their real-world deployments. Existing methods…
Large language models (LLMs) have shown potential in supporting decision-making applications, particularly as personal assistants in the financial, healthcare, and legal domains. While prompt engineering strategies have enhanced the…