24 accepted papers
We study test-time scaling, where a model improves its answer through multi-round self-reflection at inference. We introduce In-Context Policy Optimization (ICPO), in which an agent optimizes its response in context using self-assessed or externally observed rewards without modifying its parameters.…
Agent memory systems must accommodate continuously growing information while supporting efficient, context-aware retrieval for downstream tasks. Abstraction is essential for scaling agent memory, yet it often comes at the cost of specificity, obscuring the fine-grained details required for effective…
Multi-preference optimization enriches language-model alignment beyond pairwise preferences by contrasting entire sets of helpful and undesired responses, enabling richer training signals for large language models. During self-play alignment, these models often produce numerous candidate answers per…
High-quality preference data is essential for aligning foundation models with human values through preference learning. However, manual annotation of such data is often time-consuming and costly. Recent methods often adopt a self-rewarding approach, where the target model generates and annotates its…
Reward modeling in large language models is known to be susceptible to reward hacking, causing models to latch onto superficial features such as the tendency to generate lists or unnecessarily long responses. In RLHF, and more generally during post-training, flawed reward signals often lead to outpu…
Recent self-rewarding large language models (LLM) have successfully applied LLM-as-a-Judge to iteratively improve the alignment performance without the need of human annotations for preference data. These methods commonly utilize the same LLM to act as both the policy model (which generates response…
Large Language Models (LLMs) are increasingly being used to plan, reason, and execute tasks across diverse scenarios. In use cases like repeatable workflows and agentic settings, prompts are often reused with minor variations while having a similar structure for recurring tasks. This opens up opport…
Current Large Language Models excel in general reasoning yet struggle with specialized tasks requiring proprietary or domain-specific knowledge. Fine-tuning large models for every niche application is often infeasible due to black-box constraints and high computational overhead. To address this, we…
Recent Large Language Models (LLMs) have demonstrated satisfying general instruction following ability. However, small LLMs with about 7B parameters still struggle fine-grained format following (e.g., JSON format), which seriously hinder the advancements of their applications. Most existing methods…
Artificial intelligence has significantly impacted medical applications, particularly with the advent of Medical Large Vision Language Models (Med-LVLMs), sparking optimism for the future of automated and personalized healthcare. However, the trustworthiness of Med-LVLMs remains unverified, posing s…
Large language models (LLMs) enhanced with retrieval augmentation has shown great performance in many applications. However, the computational demands for these models pose a challenge when applying them to real-time tasks, such as composition assistance. To address this, we propose Hybrid Retrieval…
In-context learning has emerged as a groundbreaking ability of Large Language Models (LLMs) and revolutionized various fields by providing a few task-relevant demonstrations in the prompt. However, trustworthy issues with LLM’s response, such as hallucination, have also been actively discussed. Exis…
Early event detection aims to detect events even before the event is complete. However, most of the existing methods focus on an event with a single label but fail to be applied to cases with multiple labels. Another non-negligible issue for early event detection is a prediction with overconfidence…
Open-ended Commonsense Reasoning is defined as solving a commonsense question without providing 1) a short list of answer candidates and 2) a pre-defined answer scope. Conventional ways of formulating the commonsense question into a question-answering form or utilizing external knowledge to learn re…
Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieve state-of-the-art performance. However, the performance of existing approaches heavily depends on the inter-class variance of the support set. As a result, it can perform well on tasks when the semant…
Various contrastive learning approaches have been proposed in recent years and achieve significant empirical success. While effective and prevalent, contrastive learning has been less explored for time series data. A key component of contrastive learning is to select appropriate augmentations imposi…
"Few-shot semantic segmentation aims at learning to segment a novel object class with only a few annotated examples. Most existing methods consider a setting where base classes are sampled from the same domain as the novel classes. However, in many applications, collecting sufficient training data f…
Sound Event Early Detection (SEED) is an essential task in recognizing the acoustic environments and soundscapes. However, most of the existing methods focus on the offline sound event detection, which suffers from the over-confidence issue of early-stage event detection and usually yield unreliable…
Large-scale multilingual pre-trained language models have achieved remarkable performance in zero-shot cross-lingual tasks. A recent study has demonstrated the effectiveness of self-learning-based approach on cross-lingual transfer, where only unlabeled data of target languages are required, without…
We target the task of cross-lingual Machine Reading Comprehension (MRC) in the direct zero-shot setting, by incorporating syntactic features from Universal Dependencies (UD), and the key features we use are the syntactic relations within each sentence. While previous work has demonstrated effective…
Recent multilingual pre-trained language models have achieved remarkable zero-shot performance, where the model is only finetuned on one source language and directly evaluated on target languages. In this work, we propose a self-learning framework that further utilizes unlabeled data of target langu…
Forecasting on sparse multivariate time series (MTS) aims to model the predictors of future values of time series given their incomplete past, which is important for many emerging applications. However, most existing methods process MTS’s individually, and do not leverage the dynamic distributions u…
We consider the models of deep multi-task learning with recurrent architectures that exploit regularities across tasks to improve the performance of multiple sequence processing tasks jointly. Most existing architectures are painstakingly customized to learn task relationships for different problems…
Measuring document similarity plays an important role in natural language processing tasks. Most existing document similarity approaches suffer from the information gap caused by context and vocabulary mismatches when comparing varying-length texts. In this paper, we propose an unsupervised concept…