Chongyang Zhao

Haodong Lu, Chongyang Zhao, Jason Xue et al.

The central tension in continual learning (CL) is the trade-off between plasticity (acquiring new knowledge) and stability (retaining prior knowledge). We study how a pre-trained backbone can be continually updated to absorb new knowledge while preserving existing capabilities, via capacity control: regulating the effective rank of each parameter update, a per-step quantity directly controllable inside a LoRA update. A controlled probe of LoRA rank and placement across modules and tasks reveals a consistent trade-off, with a moderate-rank sweet spot that varies by placement and task, leaving no universally optimal fixed rank; a formal bound shows forgetting grows with rank. Building on these findings, we propose Continual Dynamic Rank-Selective LoRA (CoDyRA), which jointly trains each LoRA update with rank minimization via sparsity-promoting regularization on per-component importance weights. The supervised objective drives plasticity; rank minimization regularizes forgetting. We show that rank minimization serves as an implicit forgetting regularizer in the CL regime, protecting general capability and prior-task knowledge simultaneously by controlling forgetting against the current model state. Across MTIL, X-TAIL, and TRACE (CLIP, LLaMA, Gemma), CoDyRA outperforms prior CL methods on new knowledge learning and forgetting, achieving a strong plasticity-stability balance. Code is available at https://github.com/jeff024/codyra.

Qi Chen, Dileepa Pitawela, Chongyang Zhao et al.

Vision-and-Language Navigation (VLN) task aims to enable AI agents to accurately understand and follow natural language instructions to navigate through real-world environments, ultimately reaching specific target locations. We recognise a promising opportunity to extend VLN to a comparable navigation task that holds substantial significance in our daily lives, albeit within the virtual realm: navigating websites on the Internet. This paper proposes a new task named Vision-and-Language Navigation on Websites (WebVLN), where we use question-based instructions to train an agent, emulating how users naturally browse websites. Unlike the existing VLN task that only pays attention to vision and instruction (language), the WebVLN agent further considers underlying web-specific content like HTML, which could not be seen on the rendered web pages yet contains rich visual and textual information. Toward this goal, we contribute a dataset, WebVLN-v1, and introduce a novel approach called Website-aware VLN Network (WebVLN-Net), which is built upon the foundation of state-of-the-art VLN techniques. Experimental results show that WebVLN-Net outperforms current VLN and web-related navigation methods. We believe that the introduction of the new WebVLN task and its dataset will establish a new dimension within the VLN domain and contribute to the broader vision-and-language research community. The code is available at: https://github.com/WebVLN/WebVLN.

Haodong Lu, Chongyang Zhao, Jason Xue et al.

Continual learning (CL) aims to accumulate knowledge from sequential tasks without catastrophic forgetting. Vision-language models such as CLIP, with strong generalization, are widely used for CL. Existing methods often adapt isolated PTM components, increasing inference complexity and limiting model improvement, or rely on replay, stored data, or assumptions, leading to high costs and limited applicability. To advance models as continual learners, we explore CL through natural and efficient PTM updates rather than complex task-specific additions. We study continual low-rank learning and analyze how LoRA ranks and placements affect learning and forgetting. A higher-rank LoRA improves task learning (plasticity) but increases forgetting, while a lower-rank LoRA enhances stability but limits adaptation. We observe a plasticity-stability balance tied to rank across parameters and tasks, with moderately small ranks maximizing CL benefits. Motivated by this, we propose Continual Dynamic Rank-Selective LoRA (CoDyRA), which continually updates PTMs with LoRA adapters of adaptively optimized ranks. The new-task objective drives learning, while sparsity-promoting regularization minimizes ranks to reduce interference and forgetting, achieving a balance tailored to each parameter and task. Although all parameters are updated, the minimized ranks keep the model close to its prior state while enabling effective new-task learning. CoDyRA performs efficient CL as a sequence of LoRA-based updates without storing past data or relying on assumptions, preserving the original model architecture and adding no inference overhead. Experiments show CoDyRA improves new representations while retaining old knowledge, achieving state-of-the-art results. Code is available at https://github.com/jeff024/codyra.

Chongyang Zhao, Mingsong Li, Haodong Lu et al.

Multimodal Continual Instruction Tuning aims to continually enhance Large Vision Language Models (LVLMs) by learning from new data without forgetting previously acquired knowledge. Mixture of Experts (MoE) architectures naturally facilitate this by incrementally adding new experts and expanding routers while keeping the existing ones frozen. However, despite expert isolation, MoE-based continual learners still suffer from forgetting due to routing-drift: old-task tokens become mistakenly attracted to newly added experts, degrading performance on prior tasks. We analyze the failure mode at the token level and reveal the token's dilemma: ambiguous and old tokens in new-task data offer minimal learning benefit yet induce forgetting when routed to new experts, due to their ambiguous routing assignment during training. Motivated by this, we propose LLaVA-DyMoE, a dynamic MoE framework that incrementally expands the MoE with drift-aware token assignment. We characterize token types via their routing score distributions and apply targeted regularization. Specifically, a token-level assignment guidance steers ambiguous and old tokens away from new experts to preserve established routing patterns and alleviate routing-drift, while complementary routing score regularizations enforce expert-group separation and promote new-expert specialization. Extensive experiments demonstrate that our LLaVA-DyMoE effectively mitigates routing-drift-induced forgetting, achieving over a 7% gain in mean final accuracy and a 12% reduction in forgetting compared to baselines. The project page is https://zhaoc5.github.io/DyMoE.

Gengze Zhou, Yicong Hong, Zun Wang et al.

The academic field of learning instruction-guided visual navigation can be generally categorized into high-level category-specific search and low-level language-guided navigation, depending on the granularity of language instruction, in which the former emphasizes the exploration process, while the latter concentrates on following detailed textual commands. Despite the differing focuses of these tasks, the underlying requirements of interpreting instructions, comprehending the surroundings, and inferring action decisions remain consistent. This paper consolidates diverse navigation tasks into a unified and generic framework -- we investigate the core difficulties of sharing general knowledge and exploiting task-specific capabilities in learning navigation and propose a novel State-Adaptive Mixture of Experts (SAME) model that effectively enables an agent to infer decisions based on different-granularity language and dynamic observations. Powered by SAME, we present a versatile agent capable of addressing seven navigation tasks simultaneously that outperforms or achieves highly comparable performance to task-specific agents.

Chongyang Zhao, Dong Gong

Continual learning (CL) aims to efficiently learn from a non-stationary data stream, without storing or recomputing all seen samples. CL enables prediction on new tasks by incorporating sequential training samples. Building on this connection between CL and sequential modeling, meta-continual learning (MCL) aims to meta-learn an efficient continual learner as a sequence prediction model, with advanced sequence models like Transformers being natural choices. However, despite decent performance, Transformers rely on a linearly growing cache to store all past representations, conflicting with CL's objective of not storing all seen samples and limiting efficiency. In this paper, we focus on meta-learning sequence-prediction-based continual learners without retaining all past representations. While attention-free models with fixed-size hidden states (e.g., Linear Transformers) align with CL's essential goal and efficiency needs, they have shown limited effectiveness in MCL in previous literature. Given Mamba's strong sequence modeling performance and attention-free nature, we explore a key question: Can attention-free models like Mamba perform well on MCL? By formulating Mamba and the SSM for MCL tasks, we propose MambaCL, a meta-learned continual learner. To enhance MambaCL's training, we introduce selectivity regularization, leveraging the connection between Mamba and Transformers to guide its behavior over sequences. Furthermore, we study how Mamba and other models perform across various MCL scenarios through extensive and well-designed experiments. Our results highlight the promising performance and strong generalization of Mamba and attention-free models in MCL, demonstrating its potential for efficient continual learning and adaptation.

Haodong Lu, Chongyang Zhao, Jason Xue et al.

Continual learning (CL) with large pre-trained models is challenged by catastrophic forgetting and task interference. Existing LoRA-based Mixture-of-Experts (MoE) approaches mitigate forgetting by assigning and freezing task-specific adapters, but suffer from interference, redundancy, and ambiguous routing due to coarse adapter-level selection. However, this design introduces three key challenges: 1) Interference: Activating full LoRA experts per input leads to subspace interference and prevents selective reuse of useful components across tasks. 2) Redundancy: Newly added experts often duplicate or contradict existing knowledge due to unnecessary activation of unrelated ranks and insufficient reuse of relevant ones. 3) Ambiguity: Overlapping features across tasks confuse the router, resulting in unstable expert assignments. As more experts accumulate, earlier task routing degrades, accelerating forgetting. We propose MoRA, a Mixture-of-Rank Adaptive learning approaches with self-activated and sparse rank activation for CL. Unlike mixing multiple low-rank matrices, MoRA decomposes each rank-r update into r rank-one components, each treated as an independent expert, enabling fine-grained rank-one expert utilization while mitigating interference and redundancy. To avoid ambiguous routing, we propose that each rank-one expert can infer its own relevance via intermediate activations. Coupled with our proposed rank pruning and activation budgets, MoRA adaptively selects a sparse mixture of ranks per input. We validate MoRA on continual learning benchmarks using CLIP and language models, analyzing both in-domain learning and out-of-domain forgetting/generalization during fine-tuning. MoRA shows significant effectiveness in enhancing CL with PTMs, and improving generalization while mitigating forgetting.

Chongyang Zhao, Yuankai Qi, Qi Wu

Vision-and-Language Navigation (VLN) aims to navigate to the target location by following a given instruction. Unlike existing methods focused on predicting a more accurate action at each step in navigation, in this paper, we make the first attempt to tackle a long-ignored problem in VLN: narrowing the gap between Success Rate (SR) and Oracle Success Rate (OSR). We observe a consistently large gap (up to 9%) on four state-of-the-art VLN methods across two benchmark datasets: R2R and REVERIE. The high OSR indicates the robot agent passes the target location, while the low SR suggests the agent actually fails to stop at the target location at last. Instead of predicting actions directly, we propose to mine the target location from a trajectory given by off-the-shelf VLN models. Specially, we design a multi-module transformer-based model for learning compact discriminative trajectory viewpoint representation, which is used to predict the confidence of being a target location as described in the instruction. The proposed method is evaluated on three widely-adopted datasets: R2R, REVERIE and NDH, and shows promising results, demonstrating the potential for more future research.