Related papers: From Blind Spots to Gains: Diagnostic-Driven Itera…

Test-time adaptation, which enables models to generalize to diverse data with unlabeled test samples, holds significant value in real-world scenarios. Recently, researchers have applied this setting to advanced pre-trained vision-language…

The rapid progress of multimodal large language models (MLLMs) calls for more reliable evaluation protocols. Existing static benchmarks suffer from the potential risk of data contamination and saturation, leading to inflated or misleading…

Large Language Models (LLMs) often struggle to process and generate coherent context when the number of input tokens exceeds the pre-trained length. Recent advancements in long-context extension have significantly expanded the context…

Recent advances in large language models (LLMs) have demonstrated the effectiveness of Iterative Self-Improvement (ISI) techniques. However, continuous training on self-generated data leads to reduced output diversity, a limitation…

Ensembling large language models (LLMs) can effectively combine diverse strengths of different models, offering a promising approach to enhance performance across various tasks. However, existing methods typically rely on fixed weighting…

Deep transfer learning techniques try to tackle the limitations of deep learning, the dependency on extensive training data and the training costs, by reusing obtained knowledge. However, the current DTL techniques suffer from either…

Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, yet real-world deployment often requires continual capability expansion across sequential tasks. In such scenarios, Multimodal Continual…

Continual learning enables vision-language models to accumulate knowledge and adapt to evolving tasks without retraining from scratch. However, in multi-domain task-incremental learning, large domain shifts intensify the…

We introduce Learning to Self-Evolve (LSE), a reinforcement learning framework that trains large language models (LLMs) to improve their own contexts at test time. We situate LSE in the setting of test-time self-evolution, where a model…

Recent advancements in general-purpose or domain-specific multimodal large language models (LLMs) have witnessed remarkable progress for medical decision-making. However, they are designated for specific classification or generative tasks,…

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…

Large Multimodal Models (LMMs) have demonstrated impressive performance across numerous academic benchmarks. However, fine-tuning still remains essential to achieve satisfactory performance on downstream tasks, while the task-specific…

Learning-based autonomous driving requires continuous integration of diverse knowledge in complex traffic , yet existing methods exhibit significant limitations in adaptive capabilities. Addressing this gap demands autonomous driving…

Large language models (LLMs) have improved significantly in their reasoning through extensive training on massive datasets. However, relying solely on additional data for improvement is becoming increasingly impractical, highlighting the…

Model-based reinforcement learning attempts to use an available or learned model to improve the data efficiency of reinforcement learning. This work proposes a one-step lookback approach that jointly learns the deep incremental model and…

Dynamic multiobjective optimization problems (DMOPs) feature time-varying objectives, which cause the Pareto optimal solution (POS) set to drift over time and make it difficult to maintain both convergence and diversity under limited…

Existing model-based value expansion methods typically leverage a world model for value estimation with a fixed rollout horizon to assist policy learning. However, the fixed rollout with an inaccurate model has a potential to harm the…

Reinforcement learning with verifiable rewards (RLVR) has recently advanced the reasoning capabilities of large language models (LLMs). While prior work has emphasized algorithmic design, data curation, and reward shaping, we investigate…

Large Language Models (LLM) alignment aims to prevent models from producing content that misaligns with human expectations, which can lead to ethical and legal concerns. In the last few years, Reinforcement Learning from Human Feedback…

Evaluating large language models (LLMs) today rests on fixed benchmarks that apply the same set of items to any model, producing ceiling and floor effects that mask capability gaps. We argue that the most informative evaluation signal lies…