Related papers: Evidence-based Distributional Alignment for Large …
The recent advancement of Multimodal Large Language Models (MLLMs) is transforming human-computer interaction (HCI) from surface-level exchanges into more nuanced and emotionally intelligent communication. To realize this shift, emotion…
We address the problem of visual knowledge adaptation by leveraging labeled patterns from source domain and a very limited number of labeled instances in target domain to learn a robust classifier for visual categorization. This paper…
Large Vision-Language Models (VLMs) rely on effective multimodal alignment between pre-trained vision encoders and Large Language Models (LLMs) to integrate visual and textual information. This paper presents a comprehensive analysis of…
Linear Discriminant Analysis (LDA) is a well-known technique for feature extraction and dimension reduction. The performance of classical LDA, however, significantly degrades on the High Dimension Low Sample Size (HDLSS) data for the…
Language models (LMs) are machine learning models designed to predict linguistic patterns by estimating the probability of word sequences based on large-scale datasets, such as text. LMs have a wide range of applications in natural language…
Comprehensive evaluation of Large Language Models (LLMs) is an open research problem. Existing evaluations rely on deterministic point estimates generated via greedy decoding. However, we find that deterministic evaluations fail to capture…
Large Language Models (LLMs) exhibit world knowledge and inference capabilities, making them powerful tools for various applications. This paper proposes a feedback loop mechanism that leverages these capabilities to tune Evolution…
Recent approaches for vision-language models (VLMs) have shown remarkable success in achieving fast downstream adaptation. When applied to real-world downstream tasks, VLMs inevitably encounter both the in-distribution (ID) data and…
Existing training approaches for large language models learn a single set of parameters, based on large volumes of data, which is typically heterogeneous, conflicting and often outright contradictory. As a result, the model is forced to…
We propose LLM-Eval, a unified multi-dimensional automatic evaluation method for open-domain conversations with large language models (LLMs). Existing evaluation methods often rely on human annotations, ground-truth responses, or multiple…
Large vision-language models (LVLMs) have achieved impressive performance across multimodal tasks, but their reliance on visual inputs exposes them to adversarial threats. Encoder-based attacks provide an efficient alternative to end-to-end…
Dense retrieval calls for discriminative embeddings to represent the semantic relationship between query and document. It may benefit from the using of large language models (LLMs), given LLMs' strong capability on semantic understanding.…
Large language models show compelling performance on reasoning tasks but they tend to perform much worse in languages other than English. This is unsurprising given that their training data largely consists of English text and instructions.…
Multimodal large language models (MLLMs) struggle with numerical regression under long-tailed target distributions. Token-level supervised fine-tuning (SFT) and point-wise regression rewards bias learning toward high-density regions,…
Large language models are increasingly deployed in settings where reliability matters, yet output-level uncertainty signals such as token probabilities, entropy, and self-consistency can become brittle under calibration--deployment…
Quantifying the uncertainty of predictions made by large language models (LLMs) in binary text classification tasks remains a challenge. Calibration, in the context of LLMs, refers to the alignment between the model's predicted…
Multilingual large language models (LLMs) often demonstrate a performance gap between English and non-English languages, particularly in low-resource settings. Aligning these models to low-resource languages is essential yet challenging due…
Data attribution methods quantify the influence of training data on model outputs and are becoming increasingly relevant for a wide range of LLM research and applications, including dataset curation, model interpretability, data valuation.…
Although large language models rely on chain-of-thought for complex reasoning, the overthinking phenomenon severely degrades inference efficiency. Existing reinforcement learning methods compress reasoning chains by designing elaborate…
Edge Intelligence (EI) has been instrumental in delivering real-time, localized services by leveraging the computational capabilities of edge networks. The integration of Large Language Models (LLMs) empowers EI to evolve into the next…