Related papers: VISPA: Pluralistic Alignment via Automatic Value S…

Large Language Models (LLMs) alignment methods have been credited with the commercial success of products like ChatGPT, given their role in steering LLMs towards user-friendly outputs. However, current alignment techniques predominantly…

Large language models (LLMs) are often evaluated based on their stated values, yet these do not reliably translate into their actions, a discrepancy termed "value-action gap." In this work, we argue that this gap persists even under…

We present a novel approach for generating plausible verbal interactions between virtual human-like agents and user avatars in shared virtual environments. Sense-Plan-Ask, or SPA, extends prior work in propositional planning and natural…

If large language models operate in a universal semantic space, then switching between languages should require only a simple activation offset. To test this, we take multilingual in-context learning as a case study, where few-shot…

Generative AI has significantly changed industries by enabling text-driven image generation, yet challenges remain in achieving high-resolution outputs that align with fine-grained user preferences. Consequently, multi-round interactions…

Vision-language action (VLA) policies often report strong manipulation benchmark performance with relatively few demonstrations, but it remains unclear whether this reflects robust language-to-object grounding or reliance on…

Vision-Language-Action (VLA) models offer promising capabilities for autonomous driving through multimodal understanding. However, their utilization in safety-critical scenarios is constrained by inherent limitations, including imprecise…

Large vision language models (VLMs) combine large language models with vision encoders, demonstrating promise across various tasks. However, they often underperform in task-specific applications due to domain gaps between pre-training and…

Large Vision-Language Models (LVLMs) or multimodal large language models represent a significant advancement in artificial intelligence, enabling systems to understand and generate content across both visual and textual modalities. While…

Current large language models (LLMs) generally show a significant performance gap in alignment between English and other languages. To bridge this gap, existing research typically leverages the model's responses in English as a reference to…

A voice AI agent that blends seamlessly into daily life would interact with humans in an autonomous, real-time, and emotionally expressive manner. Rather than merely reacting to commands, it would continuously listen, reason, and respond…

Recently, prompt-based fine-tuning has garnered considerable interest as a core technique for few-shot text classification task. This approach reformulates the fine-tuning objective to align with the Masked Language Modeling (MLM)…

Direct alignment algorithms (DAAs), such as direct preference optimization (DPO), have become popular alternatives for Reinforcement Learning from Human Feedback (RLHF) due to their simplicity, efficiency, and stability. However, the…

The language ability of Large Language Models (LLMs) is often unbalanced towards English because of the imbalance in the distribution of the pre-training data. This disparity is demanded in further fine-tuning and affecting the…

Current speech encoding pipelines often rely on an additional text-based LM to get robust representations of human communication, even though SotA speech-to-text models often have a LM within. This work proposes an approach to improve the…

Audio-aware large language models (ALLMs) have recently made great strides in understanding and processing audio inputs. These models are typically adapted from text-based large language models (LLMs) through additional training on…

A prominent issue in aligning language models (LMs) to personalized preferences is underspecification -- the lack of information from users about their preferences. A popular trend of injecting such specification is adding a prefix (e.g.…

Large language models frequently exhibit suboptimal performance on low resource languages, primarily due to inefficient subword segmentation and systemic training data imbalances. In this paper, we propose Variable Entropy Policy…

Multi-prompt learning methods have emerged as an effective approach for facilitating the rapid adaptation of vision-language models to downstream tasks with limited resources. Existing multi-prompt learning methods primarily focus on…

Language models (LMs) are typically post-trained for desired capabilities and behaviors via weight-based or prompt-based steering, but the former is time-consuming and expensive, and the latter is not precisely controllable and often…