Yujie Feng, Xujia Wang, Zexin Lu, Shenghong Fu, Guangyuan Shi, Yongxin Xu, Yasha Wang, Philip S. Yu, Xu Chu, Xiao-Ming Wu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

A practical dialogue system requires the capacity for ongoing skill acquisition and adaptability to new tasks while preserving prior knowledge.However, current methods for Continual Dialogue State Tracking (DST), a crucial function of dialogue systems, struggle with the catastrophic forgetting issue and knowledge transfer between tasks.We present TaSL, a novel framework for task skill localization and consolidation that enables effective knowledge transfer without relying on memory replay.TaSL uses a novel group-wise technique to pinpoint task-specific and task-shared areas.Additionally, a fine-grained skill consolidation strategy protects task-specific knowledge from being forgotten while updating shared knowledge for bi-directional knowledge transfer.As a result, TaSL strikes a balance between preserving previous knowledge and excelling at new tasks.Comprehensive experiments on various backbones highlight the significant performance improvements of TaSL over existing state-of-the-art methods.The source code 1 is provided for reproducibility.

We present EasyGen, an efficient model designed to enhance multimodal understanding and generation by harnessing the capabilities of diffusion models and large language models (LLMs).Unlike existing multimodal models that predominately depend on encoders like CLIP or ImageBind and need ample amounts of training data to bridge modalities, Easy-Gen leverages BiDiffuser, a bidirectional conditional diffusion model, to foster more efficient modality interactions.EasyGen achieves text generation by training a projection layer linking BiDiffuser and an LLM, and facilities image generation by training an adapter to align the LLM's text space with the BiDiffuser's image space.Comprehensive quantitative and qualitative experiments show that EasyGen excels in data-efficient training, high-quality image generation, and extendibility, effectively addressing the challenges in multimodal generation.The source code is available at https: //github.com/zxy556677/EasyGen.

Zero-shot cross-domain dialogue state tracking (DST) enables us to manage task-oriented dialogues in new, unseen domains without the cost of collecting in-domain data.Previous studies have implemented slot-based input improvements, such as schema-driven descriptions and question-answering formats, but still suffer from negative transfer for seen slots and inefficient transfer for unseen slots due to the significant source-target domain gap.To address these issues, we introduce a novel framework called Context-aware Auto-prompting and Instruction-following Contrastive Decoding (CAPID).This framework generates dynamic, context-aware slot queries, effectively improving the model's transferability.Our context-aware auto-prompting approach tailors slot queries to the current dialogue context, increasing flexibility and reducing ambiguities.Additionally, an instruction-following contrastive decoding strategy helps reduce errors related to off-topic slots by penalizing deviations from the provided instructions.Extensive experiments on two datasets, with varying model sizes (from 60M to 7B), demonstrate the superior performance of CAPID.The source code 1 is provided for reproducibility.

In this paper, we take a new look at real-world image super-resolution (real-SR) from a multi-task learning perspective. We demonstrate that the conventional formulation of real-SR can be viewed as solving multiple distinct degradation tasks using a single shared model. This poses a challenge known as task competition or task conflict in multi-task learning, where certain tasks dominate the learning process, resulting in poor performance on other tasks. This problem is exacerbated in the case of real-SR, due to the involvement of numerous degradation tasks. To address the issue of task competition in real-SR, we propose a task grouping approach. Our approach efficiently identifies the degradation tasks where a real-SR model falls short and groups these unsatisfactory tasks into multiple task groups. We then utilize the task groups to fine-tune the real-SR model in a simple way, which effectively mitigates task competition and facilitates knowledge transfer. Extensive experiments demonstrate our method achieves significantly enhanced performance across a wide range of degradation scenarios.

This paper considers incremental few-shot learning, which requires a model to continually recognize new categories with only a few examples provided. Our study shows that existing methods severely suffer from catastrophic forgetting, a well-known problem in incremental learning, which is aggravated due to data scarcity and imbalance in the few-shot setting. Our analysis further suggests that to prevent catastrophic forgetting, actions need to be taken in the primitive stage -- the training of base classes instead of later few-shot learning sessions. Therefore, we propose to search for flat local minima of the base training objective function and then fine-tune the model parameters within the flat region on new tasks. In this way, the model can efficiently learn new classes while preserving the old ones. Comprehensive experimental results demonstrate that our approach outperforms all prior state-of-the-art methods and is very close to the approximate upper bound. The source code is available at https://github.com/moukamisama/F2M.