arXiv subjects

Peilin Liu

Publications and source records attributed to Peilin Liu.

At least 19 recordsLinked to original sources

arXiv2026

EVAR: Evidence-Validated Hypothesis Admission for Budget-Aware Narrative Reasoning

Large language models (LLMs) often produce fluent but weakly grounded conclusions when reasoning over non-interactive, long-form narratives. A central failure mode is that unsupported intermediate hypotheses can enter the reasoning trajectory and contaminate subsequent inference, especially when evidence is scattered across distant parts of the story. To address this problem, we propose EVAR, an evidence-validated hypothesis admission framework for budget-aware narrative reasoning. EVAR first compiles the narrative into an immutable evidence store of source-linked atomic claims and assigns an instance-specific inference budget from unresolved gaps and uncertainty signals. During refinement, EVAR directly proposes candidate hypotheses for unresolved gaps, constructs hypothesis-conditioned validation challenges, and verifies each candidate against the locked store before admission: supported hypotheses enter the answer-supporting state, unverifiable ones are quarantined, and contradictory ones are discarded. A sufficiency-based stopping mechanism further avoids unnecessary refinement. Experiments on NarraCrime and multiple public reasoning benchmarks show that EVAR improves both task performance and evidence faithfulness while maintaining controllable inference cost.

cs.CL↗

arXiv2026

Curvature-Aware Zeroth-Order Optimization for Memory-Efficient Test-Time Adaptation

Test-time adaptation (TTA) aims to enhance the cross-domain performance of pre-trained models by adapting to unlabeled test data. While most existing TTA methods rely on backpropagation (BP) for finetuning, BP-free methods such as zeroth-order (ZO) methods are more desired in practical on-device scenarios. ZO methods rely only on forward computation, which can largely reduce the complexity and memory overhead of on-device deployment. However, ZO methods suffer from much higher variance compared with first-order methods in estimating the gradient. To address this, we propose an improved ZO method to substantially boost the performance of ZO optimization based TTA. First, we provide an observation to reveal the persistent low-rank Hessian structure of the loss during the adaptation process. Based on this insight, we then propose a loss-landscape curvature-aware zeroth-order (CAZO) method, which leverages a sliding-average estimation of the diagonal Hessian to construct a covariance matrix for anisotropic perturbation sampling. CAZO operates by freezing pretrained weights and optimizing minimal adapter parameters via forward-only passes based gradient estimation, which can substantially reduce the memory overhead compared to BP-based methods. Extensive experiments demonstrate that CAZO significantly outperforms existing TTA methods, achieving state-of-the-art performance while maintaining an excellent balance between accuracy and memory efficiency. Code is available at https://github.com/Hollyming/CAZO.

cs.CV↗

arXiv2026

PinpointQA: A Benchmark for Small Object-Centric Spatial Understanding in Indoor Videos

Reliable embodied interaction in indoor environments requires agents to precisely localize small everyday objects from visual observations. Yet this fundamental capability remains challenging for multimodal large language models (MLLMs), particularly when spatial understanding must be performed from indoor videos. Existing benchmarks study video spatial intelligence and embodied reasoning, but do not directly evaluate whether a model can localize a small target object and express its position with sufficient precision. We introduce PinpointQA, a benchmark built from ScanNet++ and ScanNet200. It contains 1,024 scenes and 10,094 QA pairs across four progressively challenging tasks: Target Presence Verification, Nearest Reference Identification, Fine-Grained Spatial Description, and Structured Spatial Prediction. Ground-truth annotations are constructed from intermediate spatial representations derived from aligned 3D geometry and instance-level annotations, while evaluated models receive only sampled RGB video frames. Evaluations of representative MLLMs reveal a consistent performance decline across the task progression, with structured spatial prediction remaining particularly challenging, while supervised fine-tuning substantially improves performance. By isolating the spatial grounding capabilities that precede downstream embodied interaction, PinpointQA serves as both a diagnostic benchmark and an effective training resource. The project page is available at https://rainchowz.github.io/PinpointQA/.

cs.CV↗

arXiv2026

Ghost in the Kernel: In-Context Learning with Efficient Transformers via Domain Generalization

Transformer-based large models have demonstrated remarkable generalization abilities across different tasks by leveraging a context-aware attention module for in-context learning. With richer context, transformers adapt more effectively to the current use case without any parameter updates. However, the quadratic computational and memory complexity with respect to context length significantly slows data processing in softmax transformers. Linear transformers were proposed to address this issue by reducing the complexity to linear dependence on context length, but the design and understanding of the feature mapping in linear attention, from a theoretical viewpoint, remain unclear. In this paper, we investigate the approximation and generalization abilities of linear transformers under a two-staged sampling process from domain generalization. We show that linear transformers perform in-context learning as learning a mapping from context distributions to response functions. A dimension-independent convergence rate is obtained for our generalization analysis, which also exhibits the tradeoff between the regularities of data distributions and latent features. Guided by our theoretical framework, we propose a new perspective on activation and loss design for linearizing pretrained softmax large language models.

cs.LG↗

arXiv2026

Generalization Analysis of Transformers in Distribution Regression

In recent years, models based on the Transformer architecture have seen widespread applications and have become one of the core tools in the field of deep learning. Numerous successful techniques, such as parameter-efficient fine-tuning and efficient scaling, have been proposed surrounding their applications to further enhance performance. However, the success of these strategies has always lacked the support of rigorous mathematical theory. To study the underlying mechanisms behind Transformers and related techniques, we first propose a Transformer learning framework motivated by distribution regression, with distributions being inputs, connect a two-stage sampling process with natural language processing, and present a mathematical formulation of the attention mechanism called attention operator. We demonstrate that by the attention operator, Transformers can compress distributions into function representations without loss of information. Moreover, with the advantages of our novel attention operator, Transformers exhibit a stronger capability to learn functionals with more complex structures than convolutional neural networks and fully connected networks. Finally, we obtain a generalization bound within the distribution regression framework. Through the aforementioned theoretical results, we further discuss some successful techniques emerging with large language models (LLMs), such as prompt tuning, parameter-efficient fine-tuning, and efficient scaling. We also provide theoretical insights behind these techniques within our novel analysis framework.

stat.ML↗

arXiv2026

WPGRec: Wavelet Packet Guided Graph Enhanced Sequential Recommendation

Sequential recommendation aims to model users' evolving interests from noisy and non-stationary interaction streams, where long-term preferences, short-term intents, and localized behavioral fluctuations may coexist across temporal scales. Existing frequency-domain methods mainly rely on either global spectral operations or filter-based wavelet processing. However, global spectral operations tend to entangle local transients with long-range dependencies, while filter-based wavelet pipelines may suffer from temporal misalignment and boundary artifacts during multi-scale decomposition and reconstruction. Moreover, collaborative signals from the user-item interaction graph are often injected through scale-inconsistent auxiliary modules, limiting the benefit of jointly modeling temporal dynamics and structural dependencies. To address these issues, we propose Wavelet Packet Guided Graph Enhanced Sequential Recommendation (WPGRec), a unified time-frequency and graph-enhanced framework that aligns multi-resolution temporal modeling with graph propagation at matching scales. WPGRec first applies a full-tree undecimated stationary wavelet packet transform to generate equal-length, shift-invariant subband sequences. It then performs subband-wise interaction-graph propagation to inject high-order collaborative information while preserving temporal alignment across resolutions. Finally, an energy- and spectral-flatness-aware gated fusion module adaptively aggregates informative subbands and suppresses noise-like components. Extensive experiments on four public benchmarks show that WPGRec consistently outperforms sequential and graph-based baselines, with particularly clear gains on sparse and behaviorally complex datasets, highlighting the effectiveness of band-consistent structure injection and adaptive subband fusion for sequential recommendation.

cs.IR↗

arXiv2026

Self-Awareness before Action: Mitigating Logical Inertia via Proactive Cognitive Awareness

Large language models perform well on many reasoning tasks, yet they often lack awareness of whether their current knowledge or reasoning state is complete. In non-interactive puzzle settings, the narrative is fixed and the underlying structure is hidden; once a model forms an early hypothesis under incomplete premises, it can propagate that error throughout the reasoning process, leading to unstable conclusions. To address this issue, we propose SABA, a reasoning framework that explicitly introduces self-awareness of missing premises before making the final decision. SABA formulates reasoning as a recursive process that alternates between structured state construction and obstacle resolution: it first applies Information Fusion to consolidate the narrative into a verifiable base state, and then uses Query-driven Structured Reasoning to identify and resolve missing or underspecified premises by turning them into queries and progressively completing the reasoning state through hypothesis construction and state refinement. Across multiple evaluation metrics, SABA achieves the best performance on all three difficulty splits of the non-interactive Detective Puzzle benchmark, and it also maintains leading results on multiple public benchmarks.

cs.AI↗

arXiv2026

A Robust 3D Registration Method via Simultaneous Inlier Identification and Model Estimation

Robust 3D registration is a fundamental problem in computer vision and robotics, where the goal is to estimate the geometric transformation between two sets of measurements in the presence of noise, mismatches, and extreme outlier contamination. Existing robust registration methods are mainly built on either maximum consensus (MC) estimators, which first identify inliers and then estimate the transformation, or M-estimators, which directly optimize a robust objective. In this work, we revisit a truncated-loss based formulation for simultaneous inlier identification and model estimation (SIME) and study it in the context of 3D registration. We show that, compared with MC-based robust fitting, SIME can achieve a lower fitting residual because it incorporates residual magnitudes into the inlier selection process. To solve the resulting nonconvex problem, we develop an alternating minimization (AM) algorithm, and further propose an AM method embedded with semidefinite relaxation (SDR) to alleviate the difficulty caused by the binary inlier variables. We instantiate the proposed framework for 3D rotation search and rigid point-set registration using quaternion-based formulations. Experimental results on both simulated and real-world registration tasks demonstrate that the proposed methods compare favorably with strong baseline solvers, especially in challenging cases with high noise levels and many outliers.

cs.CV↗

arXiv2026

Boosting Vision-Language-Action Finetuning with Feasible Action Neighborhood Prior

In real-world robotic manipulation, states typically admit a neighborhood of near-equivalent actions. That is, for each state, there exist a feasible action neighborhood (FAN) rather than a single correct action, within which motions yield indistinguishable progress. However, prevalent VLA training methodologies are directly inherited from linguistic settings and do not exploit the FAN property, thus leading to poor generalization and low sample efficiency. To address this limitation, we introduce a FAN-guided regularizer that shapes the model's output distribution to align with the geometry of FAN. Concretely, we introduce a Gaussian prior that promotes locally smooth and unimodal predictions around the preferred direction and magnitude. In extensive experiments across both reinforced finetuning (RFT) and supervised finetuning (SFT), our method achieves significant improvement in sample efficiency, and success rate in both in-distribution and out-of-distribution (OOD) scenarios. By aligning with the intrinsic action tolerance of physical manipulation, FAN-guided regularization provides a principled and practical method for sample-efficient, and generalizable VLA adaptation.

cs.RO↗

arXiv2026

SSMG-Nav: Enhancing Lifelong Object Navigation with Semantic Skeleton Memory Graph

Navigating to out-of-sight targets from human instructions in unfamiliar environments is a core capability for service robots. Despite substantial progress, most approaches underutilize reusable, persistent memory, constraining performance in lifelong settings. Many are additionally limited to single-modality inputs and employ myopic greedy policies, which often induce inefficient back-and-forth maneuvers (BFMs). To address such limitations, we introduce SSMG-Nav, a framework for object navigation built on a \textit{Semantic Skeleton Memory Graph} (SSMG) that consolidates past observations into a spatially aligned, persistent memory anchored by topological keypoints (e.g., junctions, room centers). SSMG clusters nearby entities into subgraphs, unifying entity- and space-level semantics to yield a compact set of candidate destinations. To support multimodal targets (images, objects, and text), we integrate a vision-language model (VLM). For each subgraph, a multimodal prompt synthesized from memory guides the VLM to infer a target belief over destinations. A long-horizon planner then trades off this belief against traversability costs to produce a visit sequence that minimizes expected path length, thereby reducing backtracking. Extensive experiments on challenging lifelong benchmarks and standard ObjectNav benchmarks demonstrate that, compared to strong baselines, our method achieves higher success rates and greater path efficiency, validating the effectiveness of SSMG-Nav.

cs.RO↗

arXiv2025

A Skeleton-Based Topological Planner for Exploration in Complex Unknown Environments

The capability of autonomous exploration in complex, unknown environments is important in many robotic applications. While recent research on autonomous exploration have achieved much progress, there are still limitations, e.g., existing methods relying on greedy heuristics or optimal path planning are often hindered by repetitive paths and high computational demands. To address such limitations, we propose a novel exploration framework that utilizes the global topology information of observed environment to improve exploration efficiency while reducing computational overhead. Specifically, global information is utilized based on a skeletal topological graph representation of the environment geometry. We first propose an incremental skeleton extraction method based on wavefront propagation, based on which we then design an approach to generate a lightweight topological graph that can effectively capture the environment's structural characteristics. Building upon this, we introduce a finite state machine that leverages the topological structure to efficiently plan coverage paths, which can substantially mitigate the back-and-forth maneuvers (BFMs) problem. Experimental results demonstrate the superiority of our method in comparison with state-of-the-art methods. The source code will be made publicly available at: https://github.com/Haochen-Niu/STGPlanner.

cs.RO↗

arXiv2025

A High-Throughput Spiking Neural Network Processor Enabling Synaptic Delay Emulation

Synaptic delay has attracted significant attention in neural network dynamics for integrating and processing complex spatiotemporal information. This paper introduces a high-throughput Spiking Neural Network (SNN) processor that supports synaptic delay-based emulation for edge applications. The processor leverages a multicore pipelined architecture with parallel compute engines, capable of real-time processing of the computational load associated with synaptic delays. We develop a SoC prototype of the proposed processor on PYNQ Z2 FPGA platform and evaluate its performance using the Spiking Heidelberg Digits (SHD) benchmark for low-power keyword spotting tasks. The processor achieves 93.4% accuracy in deployment and an average throughput of 104 samples/sec at a typical operating frequency of 125 MHz and 282 mW power consumption.

cs.NE↗

arXiv2025

An Online Adaptation Method for Robust Depth Estimation and Visual Odometry in the Open World

Recently, learning-based robotic navigation systems have gained extensive research attention and made significant progress. However, the diversity of open-world scenarios poses a major challenge for the generalization of such systems to practical scenarios. Specifically, learned systems for scene measurement and state estimation tend to degrade when the application scenarios deviate from the training data, resulting to unreliable depth and pose estimation. Toward addressing this problem, this work aims to develop a visual odometry system that can fast adapt to diverse novel environments in an online manner. To this end, we construct a self-supervised online adaptation framework for monocular visual odometry aided by an online-updated depth estimation module. Firstly, we design a monocular depth estimation network with lightweight refiner modules, which enables efficient online adaptation. Then, we construct an objective for self-supervised learning of the depth estimation module based on the output of the visual odometry system and the contextual semantic information of the scene. Specifically, a sparse depth densification module and a dynamic consistency enhancement module are proposed to leverage camera poses and contextual semantics to generate pseudo-depths and valid masks for the online adaptation. Finally, we demonstrate the robustness and generalization capability of the proposed method in comparison with state-of-the-art learning-based approaches on urban, in-house datasets and a robot platform. Code is publicly available at: https://github.com/jixingwu/SOL-SLAM.

cs.RO↗

arXiv2025

Analyzing and Bridging the Gap between Maximizing Total Reward and Discounted Reward in Deep Reinforcement Learning

The optimal objective is a fundamental aspect of reinforcement learning (RL), as it determines how policies are evaluated and optimized. While total return maximization is the ideal objective in RL, discounted return maximization is the practical objective due to its stability. This can lead to a misalignment of objectives. To better understand the problem, we theoretically analyze the performance gap between the policy maximizes the total return and the policy maximizes the discounted return. Our analysis reveals that increasing the discount factor can be ineffective at eliminating this gap when environment contains cyclic states,a frequent scenario. To address this issue, we propose two alternative approaches to align the objectives. The first approach achieves alignment by modifying the terminal state value, treating it as a tunable hyper-parameter with its suitable range defined through theoretical analysis. The second approach focuses on calibrating the reward data in trajectories, enabling alignment in practical Deep RL applications using off-policy algorithms. This method enhances robustness to the discount factor and improve performance when the trajectory length is large. Our proposed methods demonstrate that adjusting reward data can achieve alignment, providing an insight that can be leveraged to design new optimization objectives to fundamentally enhance the performance of RL algorithms.

cs.LG↗

arXiv2024

Explicit Mutual Information Maximization for Self-Supervised Learning

Recently, self-supervised learning (SSL) has been extensively studied. Theoretically, mutual information maximization (MIM) is an optimal criterion for SSL, with a strong theoretical foundation in information theory. However, it is difficult to directly apply MIM in SSL since the data distribution is not analytically available in applications. In practice, many existing methods can be viewed as approximate implementations of the MIM criterion. This work shows that, based on the invariance property of MI, explicit MI maximization can be applied to SSL under a generic distribution assumption, i.e., a relaxed condition of the data distribution. We further illustrate this by analyzing the generalized Gaussian distribution. Based on this result, we derive a loss function based on the MIM criterion using only second-order statistics. We implement the new loss for SSL and demonstrate its effectiveness via extensive experiments.

cs.CV↗

arXiv2024

Towards Scalable Automated Alignment of LLMs: A Survey

Alignment is the most critical step in building large language models (LLMs) that meet human needs. With the rapid development of LLMs gradually surpassing human capabilities, traditional alignment methods based on human-annotation are increasingly unable to meet the scalability demands. Therefore, there is an urgent need to explore new sources of automated alignment signals and technical approaches. In this paper, we systematically review the recently emerging methods of automated alignment, attempting to explore how to achieve effective, scalable, automated alignment once the capabilities of LLMs exceed those of humans. Specifically, we categorize existing automated alignment methods into 4 major categories based on the sources of alignment signals and discuss the current status and potential development of each category. Additionally, we explore the underlying mechanisms that enable automated alignment and discuss the essential factors that make automated alignment technologies feasible and effective from the fundamental role of alignment.

cs.CL↗

arXiv2024

Symmetry Awareness Encoded Deep Learning Framework for Brain Imaging Analysis

The heterogeneity of neurological conditions, ranging from structural anomalies to functional impairments, presents a significant challenge in medical imaging analysis tasks. Moreover, the limited availability of well-annotated datasets constrains the development of robust analysis models. Against this backdrop, this study introduces a novel approach leveraging the inherent anatomical symmetrical features of the human brain to enhance the subsequent detection and segmentation analysis for brain diseases. A novel Symmetry-Aware Cross-Attention (SACA) module is proposed to encode symmetrical features of left and right hemispheres, and a proxy task to detect symmetrical features as the Symmetry-Aware Head (SAH) is proposed, which guides the pretraining of the whole network on a vast 3D brain imaging dataset comprising both healthy and diseased brain images across various MRI and CT. Through meticulous experimentation on downstream tasks, including both classification and segmentation for brain diseases, our model demonstrates superior performance over state-of-the-art methodologies, particularly highlighting the significance of symmetry-aware learning. Our findings advocate for the effectiveness of incorporating symmetry awareness into pretraining and set a new benchmark for medical imaging analysis, promising significant strides toward accurate and efficient diagnostic processes. Code is available at https://github.com/bitMyron/sa-swin.

eess.IV↗

arXiv2024

Probing Implicit Bias in Semi-gradient Q-learning: Visualizing the Effective Loss Landscapes via the Fokker--Planck Equation

Semi-gradient Q-learning is applied in many fields, but due to the absence of an explicit loss function, studying its dynamics and implicit bias in the parameter space is challenging. This paper introduces the Fokker--Planck equation and employs partial data obtained through sampling to construct and visualize the effective loss landscape within a two-dimensional parameter space. This visualization reveals how the global minima in the loss landscape can transform into saddle points in the effective loss landscape, as well as the implicit bias of the semi-gradient method. Additionally, we demonstrate that saddle points, originating from the global minima in loss landscape, still exist in the effective loss landscape under high-dimensional parameter spaces and neural network settings. This paper develop a novel approach for probing implicit bias in semi-gradient Q-learning.

cs.LG↗