arXiv subjects

Juntao Lyu

Publications and source records attributed to Juntao Lyu.

3 recordsLinked to original sources

arXiv2026

Toward Robust Open-set Adaptation: Synapse Consolidation Inspired by Rac1/MAPK Pathways

Large Language Models (LLMs) generalize across tasks through reusable representations and flexible reasoning, yet remain brittle in real deployment when faced with evolving tasks and continual distribution shift. While test-time adaptation addresses this by updating models with unsupervised objectives on test data, prevailing methods are fundamentally limited by their neglect of source knowledge preservation and adaptation signal reliability. Inspired by how Drosophila orchestrates memory update by balancing retroactive and proactive interference via Rac1 and MAPK pathways, we design Synapse Consolidation (SyCo) with two core components: a Rac1-inspired plasticity confiner and a MAPK-inspired update controller. The former dynamically confines plasticity to a tail-gradient subspace that is less critical for source knowledge, enabling rapid specialization while preserving source representations. The latter uses a tiered controller to suppress noisy updates and consolidate useful adaptations under non-stationary streams. To further model real deployments with multiple sources and continually emerging tasks, we introduce Multi-source Open-set Adaptation (MOA) setting, where a model is trained on multiple labeled source tasks and then adapts on open, non-stationary unlabeled test streams mixing seen and unseen tasks with partial overlap in label and intent space. Across 18 NLP datasets under the MOA setting, SyCo consistently outperforms strong baselines, achieving 78.31\% on unseen-task adaptation and 85.37\% versus unseen-data shifts, setting a new state-of-the-art.

cs.LG↗

arXiv2025

XYZCylinder: Towards Compatible Feed-Forward 3D Gaussian Splatting for Driving Scenes via Unified Cylinder Lifting Method

Feed-forward paradigms for 3D reconstruction have become a focus of recent research, which learn implicit, fixed view transformations to generate a single scene representation. However, their application to complex driving scenes reveals significant limitations. Two core challenges are responsible for this performance gap. First, the reliance on a fixed view transformation hinders compatibility to varying camera configurations. Second, the inherent difficulty of learning complex driving scenes from sparse 360° views with minimal overlap compromises the final reconstruction fidelity. To handle these difficulties, we introduce XYZCylinder, a novel method built upon a unified cylinder lifting method that integrates camera modeling and feature lifting. To tackle the compatibility problem, we design a Unified Cylinder Camera Modeling (UCCM) strategy. This strategy explicitly models projection parameters to unify diverse camera setups, thus bypassing the need for learning viewpoint-dependent correspondences. To improve the reconstruction accuracy, we propose a hybrid representation with several dedicated modules based on newly designed Cylinder Plane Feature Group (CPFG) to lift 2D image features to 3D space. Extensive evaluations confirm that XYZCylinder not only achieves state-of-the-art performance under different evaluation settings but also demonstrates remarkable compatibility in entirely new scenes with different camera settings in a zero-shot manner. Project page: \href{https://yuyuyu223.github.io/XYZCYlinder-projectpage/}{here}

cs.CV↗

arXiv2025

CSCE: Boosting LLM Reasoning by Simultaneous Enhancing of Causal Significance and Consistency

Chain-based reasoning methods like chain of thought (CoT) play a rising role in solving reasoning tasks for large language models (LLMs). However, the causal hallucinations between a step of reasoning and corresponding state transitions are becoming a significant obstacle to advancing LLMs' reasoning capabilities, especially in long-range reasoning tasks. This paper proposes a non-chain-based reasoning framework for simultaneous consideration of causal significance and consistency, i.e., the Causal Significance and Consistency Enhancer (CSCE). We customize LLM's loss function utilizing treatment effect assessments to enhance its reasoning ability from two aspects: causal significance and consistency. This ensures that the model captures essential causal relationships and maintains robust and consistent performance across various scenarios. Additionally, we transform the reasoning process from the cascading multiple one-step reasoning commonly used in Chain-Based methods, like CoT, to a causal-enhanced method that outputs the entire reasoning process in one go, further improving the model's reasoning efficiency. Extensive experiments show that our method improves both the reasoning success rate and speed. These improvements further demonstrate that non-chain-based methods can also aid LLMs in completing reasoning tasks.

cs.CL↗