Searcharxiv⌕ Search

arXiv subjects

Kwang-Ting Cheng

Publications and source records attributed to Kwang-Ting Cheng.

At least 19 recordsLinked to original sources
arXiv2026

RAEM: Robust Autonomous Exploration for Multi-Floor Environments with a Quadruped Robot

In this paper, we propose RAEM, a robust autonomous exploration framework for quadruped robots operating in multi-floor environments. Most existing ground-robot exploration approaches rely on planar traversability representations, which cannot adequately represent the overlapping structures and cross-floor connectivity of multi-floor buildings. Although tomography-based representations provide effective traversability modeling for multi-floor navigation, maintaining a global tomography map incurs substantial computational overhead for online exploration with frequent replanning. Moreover, sparse and fragmented LiDAR observations in stairwells can degrade local traversability estimation, leading to irregular viewpoint placement and temporary topological disconnections. To address these challenges, RAEM adopts a hybrid local-global traversability representation, in which a local tomography map and an explicitly categorized local 3D grid map are used for online terrain analysis and connectivity evaluation, while an elevation-aware global topological graph is incrementally constructed from these local spatial representations for efficient cross-floor exploration planning. We further introduce a staircase center alignment strategy to reduce abrupt yaw variations during climbing and a dual path searching mechanism to recover guidance paths when the global topology is locally disconnected. Extensive simulation and real-world experiments demonstrate robust and computationally stable autonomous exploration across multi-floor structures, including continuous exploration of a five-floor stairwell.

cs.RO↗
arXiv2026

31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding

This work presents a 55nm speculative decoding-based LLM accelerator with bumping-based face-to-face ReRAM-on-logic stacking technology. It features a local rotation unit for outlier-free low-bit quantization, a stacking-aware PNM architecture co-designed with blockwise vector quantization to reduce weight EMA overheads, and an adaptive parallel speculative decoding scheme with an out-of-order scheduler for high resource and bandwidth utilization. Our chip achieves 14.08-to-135.69token/s and 4.46-to-7.17x speedup over vanilla speculative decoding.

cs.AR↗
arXiv2026

Expert Streaming: Accelerating Low-Batch MoE Inference via Multi-chiplet Architecture and Dynamic Expert Trajectory Scheduling

Mixture-of-Experts is a promising approach for edge AI with low-batch inference. Yet, on-device deployments often face limited on-chip memory and severe workload imbalance; the prevalent use of offloading further incurs off-chip memory access bottlenecks. Moreover, MoE sparsity and dynamic gating shift distributed strategies toward much finer granularity and introduce runtime scheduling considerations. Recently, high die-to-die bandwidth chiplet interconnects have created new opportunities for multi-chiplet systems to address workload imbalance and offloading bottlenecks with fine-grained scheduling. In this paper, we propose Fully Sharded Expert Data Parallelism, a parallelization paradigm specifically architected for low-batch MoE inference on multi-chiplet accelerators. FSE-DP attains adaptive computation-communication overlap and balanced load by orchestrating fine-grained, complementary expert streams along dynamic trajectories across high-bandwidth D2D links. The attendant dataflow complexity is tamed by a minimal, hardware-amenable set of virtualization rules and a lightweight scheduling algorithm. Our approach achieves 1.22 to 2.00 times speedup over state-of-the-art baselines and saves up to 78.8 percent on-chip memory.

cs.AR↗
arXiv2026

Path-Decoupled Hyperbolic Flow Matching for Few-Shot Adaptation

Recent advances in cross-modal few-shot adaptation treat visual-semantic alignment as a continuous feature transport problem via Flow Matching (FM). However, we argue that Euclidean-based FM overlooks fundamental limitations of flat geometry, where polynomial volume growth fails to accommodate diverse feature distributions, leading to severe path entanglement. To this end, we propose path-decoupled Hyperbolic Flow Matching (HFM), leveraging the Lorentz manifold's exponential expansion for trajectory decoupling. HFM structures the transport via two key designs: 1) Centripetal hyperbolic alignment: It constructs a centripetal hierarchy by anchoring textual roots, which pushes visual leaves to the boundary to initialize orderly flows. 2) Path-decoupled objective: It acts as a ``semantic guardrail'' rigidly confining trajectories within isolated class-specific geodesic corridors via step-wise supervision. Furthermore, we devise an adaptive diameter-based stopping to prevent over-transportation into the crowded origin based on the intrinsic semantic scale. Extensive ablations on 11 benchmarks have shown that HFM establishes a new state-of-the-art, consistently outperforming its Euclidean counterparts. Our codes and models will be released.

cs.CV↗
arXiv2026

A Deployment-Friendly Foundational Framework for Efficient Computational Pathology

Pathology foundation models (PFMs) generalize well across computational pathology tasks but remain costly for gigapixel whole-slide image analysis. Here, we present LitePath, a deployment-friendly framework that addresses model over-parameterization and patch-level redundancy. LitePath combines LiteFM, a compact model distilled from Virchow2, H-Optimus-1 and UNI2 using 190 million patches, with the Adaptive Patch Selector for task-specific patch selection. Compared with Virchow2, LitePath uses 28x fewer parameters and 403.5x fewer FLOPs. On an NVIDIA Jetson Orin Nano Super, it processes 208 slides per hour, 104.5x faster than Virchow2, and consumes 0.36 kWh per 3,000 slides, 171x less energy than Virchow2 on an RTX 3090 GPU. We evaluated LitePath on 45 multicenter cohorts across four organs and 33 tasks, comprising 37 classification and 8 survival cohorts, including 33 internal, 10 external and 2 prospective cohorts, with 17,837 slides from 9,977 patients disjoint from the pretraining data. Among 22 PFMs, LitePath achieved the best average rank (6.56 vs. 6.58 for Virchow2), retained 99.71% of Virchow2's Macro-AUC across classification cohorts, and improved mean C-index by 2.14 percentage points across survival cohorts (71.91% vs. 69.77%). We further introduce the Deployability Score (D-Score), a weighted geometric mean of normalized task performance and FLOPs. LitePath achieved the highest D-Score (0.8455), outperforming H0-mini (0.7723) and Virchow2 (0.7297). In a randomized paired crossover study of four pathologists and 120 cases, LitePath increased diagnostic accuracy by 4.1-15.8 percentage points and reduced diagnostic time by 10.9-14.2%. These results demonstrate rapid, cost-effective and energy-efficient pathology image analysis on accessible hardware while maintaining competitive performance.

cs.CV↗
arXiv2026

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

As language models become increasingly capable, users expect them to provide not only accurate responses but also behaviors aligned with diverse human preferences across a variety of scenarios. To achieve this, Reinforcement learning (RL) pipelines have begun incorporating multiple rewards, each capturing a distinct preference, to guide models toward these desired behaviors. However, recent work has defaulted to apply Group Relative Policy Optimization (GRPO) under multi-reward setting without examining its suitability. In this paper, we demonstrate that directly applying GRPO to normalize distinct rollout reward combinations causes them to collapse into identical advantage values, reducing the resolution of the training signal and resulting in suboptimal convergence and, in some cases, early training failure. We then introduce Group reward-Decoupled Normalization Policy Optimization (GDPO), a new policy optimization method to resolve these issues by decoupling the normalization of individual rewards, more faithfully preserving their relative differences and enabling more accurate multi-reward optimization, along with substantially improved training stability. We compare GDPO with GRPO across three tasks: tool calling, math reasoning, and coding reasoning, evaluating both correctness metrics (accuracy, bug ratio) and constraint adherence metrics (format, length). Across all settings, GDPO consistently outperforms GRPO, demonstrating its effectiveness and generalizability for multi-reward reinforcement learning optimization.

cs.CL↗
arXiv2025

A Study of Finetuning Video Transformers for Multi-view Geometry Tasks

This paper presents an investigation of vision transformer learning for multi-view geometry tasks, such as optical flow estimation, by fine-tuning video foundation models. Unlike previous methods that involve custom architectural designs and task-specific pretraining, our research finds that general-purpose models pretrained on videos can be readily transferred to multi-view problems with minimal adaptation. The core insight is that general-purpose attention between patches learns temporal and spatial information for geometric reasoning. We demonstrate that appending a linear decoder to the Transformer backbone produces satisfactory results, and iterative refinement can further elevate performance to stateof-the-art levels. This conceptually simple approach achieves top cross-dataset generalization results for optical flow estimation with end-point error (EPE) of 0.69, 1.78, and 3.15 on the Sintel clean, Sintel final, and KITTI datasets, respectively. Our method additionally establishes a new record on the online test benchmark with EPE values of 0.79, 1.88, and F1 value of 3.79. Applications to 3D depth estimation and stereo matching also show strong performance, illustrating the versatility of video-pretrained models in addressing geometric vision tasks.

cs.CV↗
arXiv2025

DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning

Reasoning language models such as OpenAI-o1, DeepSeek-R1, and Qwen achieve strong performance via extended chains of thought but often generate unnecessarily long outputs. Maximizing intelligence per token--accuracy relative to response length--remains an open problem. We revisit reinforcement learning (RL) with the simplest length penalty--truncation--and show that accuracy degradation arises not from the lack of sophisticated penalties but from inadequate RL optimization. We identify three key challenges: (i) large bias in advantage estimation, (ii) entropy collapse, and (iii) sparse reward signal. We address them with Doing Length pEnalty Right (DLER), a training recipe combining batch-wise reward normalization, higher clipping, dynamic sampling, and a simple truncation length penalty. DLER achieves state-of-the-art accuracy--efficiency trade-offs, cutting output length by over 70 percent while surpassing all previous baseline accuracy. It also improves test-time scaling: compared to DeepSeek-R1-7B, DLER-7B generates multiple concise responses in parallel with 28 percent higher accuracy and lower latency. We further introduce Difficulty-Aware DLER, which adaptively tightens truncation on easier questions for additional efficiency gains. We also propose an update-selective merging method that preserves baseline accuracy while retaining the concise reasoning ability of the DLER model, which is useful for scenarios where RL training data is scarce.

cs.LG↗
arXiv2025

Token Merging via Spatiotemporal Information Mining for Surgical Video Understanding

Vision Transformer models have shown impressive effectiveness in the surgical video understanding tasks through long-range dependency modeling. However, current methods suffer from prohibitive computational costs due to processing massive spatiotemporal tokens across video frames. While prior work on token merging has advanced model efficiency, they fail to adequately consider the inherent spatiotemporal structure of video data and overlook the heterogeneous nature of information distribution, leading to suboptimal performance. In this paper, we propose a spatiotemporal information mining token merging (STIM-TM) method, representing the first dedicated approach for surgical video understanding. STIM-TM introduces a decoupled strategy that reduces token redundancy along temporal and spatial dimensions independently. Specifically, the temporal component merges spatially corresponding tokens from consecutive frames using saliency weighting, preserving critical sequential information and maintaining continuity. Meanwhile, the spatial component prioritizes merging static tokens through temporal stability analysis, protecting dynamic regions containing essential surgical information. Operating in a training-free manner, STIM-TM achieves significant efficiency gains with over $65\%$ GFLOPs reduction while preserving competitive accuracy across comprehensive surgical video tasks. Our method also supports efficient training of long-sequence surgical videos, addressing computational bottlenecks in surgical applications.

cs.CV↗
arXiv2025

Rethinking Boundary Detection in Deep Learning-Based Medical Image Segmentation

Medical image segmentation is a pivotal task within the realms of medical image analysis and computer vision. While current methods have shown promise in accurately segmenting major regions of interest, the precise segmentation of boundary areas remains challenging. In this study, we propose a novel network architecture named CTO, which combines Convolutional Neural Networks (CNNs), Vision Transformer (ViT) models, and explicit edge detection operators to tackle this challenge. CTO surpasses existing methods in terms of segmentation accuracy and strikes a better balance between accuracy and efficiency, without the need for additional data inputs or label injections. Specifically, CTO adheres to the canonical encoder-decoder network paradigm, with a dual-stream encoder network comprising a mainstream CNN stream for capturing local features and an auxiliary StitchViT stream for integrating long-range dependencies. Furthermore, to enhance the model's ability to learn boundary areas, we introduce a boundary-guided decoder network that employs binary boundary masks generated by dedicated edge detection operators to provide explicit guidance during the decoding process. We validate the performance of CTO through extensive experiments conducted on seven challenging medical image segmentation datasets, namely ISIC 2016, PH2, ISIC 2018, CoNIC, LiTS17, and BTCV. Our experimental results unequivocally demonstrate that CTO achieves state-of-the-art accuracy on these datasets while maintaining competitive model complexity. The codes have been released at: https://github.com/xiaofang007/CTO.

eess.IV↗
arXiv2025

Relation-R1: Progressively Cognitive Chain-of-Thought Guided Reinforcement Learning for Unified Relation Comprehension

Recent advances in multi-modal large language models (MLLMs) have significantly improved object-level grounding and region captioning. However, they remain limited in visual relation understanding, struggling even with binary relation detection, let alone \textit{N}-ary relations involving multiple semantic roles. The core reason is the lack of modeling for \textit{structural semantic dependencies} among multi-entities, leading to unreliable outputs, hallucinations, and over-reliance on language priors (\eg, defaulting to ``person drinks a milk'' if a person is merely holding it). To this end, we propose Relation-R1, the \textit{first unified} relation comprehension framework that explicitly integrates cognitive chain-of-thought (CoT)-guided supervised fine-tuning (SFT) and group relative policy optimization (GRPO) within a reinforcement learning (RL) paradigm. Specifically, we first establish foundational reasoning capabilities via SFT, enforcing structured outputs with thinking processes. Then, GRPO is utilized to refine these outputs via multi-rewards optimization, prioritizing visual-semantic grounding over language-induced biases, thereby improving generalization capability. Furthermore, we investigate the impact of various CoT strategies within this framework, demonstrating that a specific-to-general progressive approach in CoT guidance further improves generalization, especially in capturing synonymous \textit{N}-ary relations. Extensive experiments on widely-used PSG and SWiG datasets demonstrate that Relation-R1 achieves state-of-the-art performance in both binary and \textit{N}-ary relation understanding.

cs.CV↗
arXiv2025

APSQ: Additive Partial Sum Quantization with Algorithm-Hardware Co-Design

DNN accelerators, significantly advanced by model compression and specialized dataflow techniques, have marked considerable progress. However, the frequent access of high-precision partial sums (PSUMs) leads to excessive memory demands in architectures utilizing input/weight stationary dataflows. Traditional compression strategies have typically overlooked PSUM quantization, which may account for 69% of power consumption. This study introduces a novel Additive Partial Sum Quantization (APSQ) method, seamlessly integrating PSUM accumulation into the quantization framework. A grouping strategy that combines APSQ with PSUM quantization enhanced by a reconfigurable architecture is further proposed. The APSQ performs nearly lossless on NLP and CV tasks across BERT, Segformer, and EfficientViT models while compressing PSUMs to INT8. This leads to a notable reduction in energy costs by 28-87%. Extended experiments on LLaMA2-7B demonstrate the potential of APSQ for large language models. Code is available at https://github.com/Yonghao-Tan/APSQ.

cs.AR↗
arXiv2025

SR-LIO++: LiDAR-Inertial Odometry and Quantized Mapping with Caching-Aware Sweep Reconstruction

Addressing the inherent low acquisition frequency limitation of 3D LiDAR to achieve high-frequency output has become a critical research focus in the LiDAR-Inertial Odometry (LIO) domain. To ensure real-time performance, frequency-enhanced LIO systems must process each sweep within significantly reduced timeframe, which presents substantial challenges for deployment on resource-constrained platforms. To address these limitations, we introduce SR-LIO++, an innovative LIO system capable of achieving doubled output frequency relative to input frequency on resource-constrained hardware platforms, including the Raspberry Pi 4B. Our system employs the previously proposed sweep reconstruction methodology to enhance LiDAR sweep frequency, generating high-frequency reconstructed sweeps. Building upon this foundation, we propose a caching mechanism for intermediate results (i.e., surface parameters) of the most recent segments, effectively minimizing redundant processing of common segments in adjacent reconstructed sweeps. This method decouples processing time from the traditionally linear dependence on reconstructed sweep frequency. Furthermore, we present a quantized map point management based on index table mapping, significantly reducing memory usage by converting global 3D point storage from 64-bit double precision to 8-bit char representation. This method also converts the computationally intensive Euclidean distance calculations in nearest neighbor searches from 64-bit double precision to 16-bit short and 32-bit integer formats, reducing computational cost. Extensive experimental evaluations across three distinct computing platforms and four public datasets demonstrate that SR-LIO++ maintains state-of-the-art accuracy while substantially enhancing efficiency. Notably, our system successfully achieves 20 Hz state output on Raspberry Pi 4B hardware.

cs.RO↗
arXiv2025

Memory Efficient Transformer Adapter for Dense Predictions

While current Vision Transformer (ViT) adapter methods have shown promising accuracy, their inference speed is implicitly hindered by inefficient memory access operations, e.g., standard normalization and frequent reshaping. In this work, we propose META, a simple and fast ViT adapter that can improve the model's memory efficiency and decrease memory time consumption by reducing the inefficient memory access operations. Our method features a memory-efficient adapter block that enables the common sharing of layer normalization between the self-attention and feed-forward network layers, thereby reducing the model's reliance on normalization operations. Within the proposed block, the cross-shaped self-attention is employed to reduce the model's frequent reshaping operations. Moreover, we augment the adapter block with a lightweight convolutional branch that can enhance local inductive biases, particularly beneficial for the dense prediction tasks, e.g., object detection, instance segmentation, and semantic segmentation. The adapter block is finally formulated in a cascaded manner to compute diverse head features, thereby enriching the variety of feature representations. Empirically, extensive evaluations on multiple representative datasets validate that META substantially enhances the predicted quality, while achieving a new state-of-the-art accuracy-efficiency trade-off. Theoretically, we demonstrate that META exhibits superior generalization capability and stronger adaptability.

cs.CV↗
arXiv2025

Generalized Task-Driven Medical Image Quality Enhancement with Gradient Promotion

Thanks to the recent achievements in task-driven image quality enhancement (IQE) models like ESTR, the image enhancement model and the visual recognition model can mutually enhance each other's quantitation while producing high-quality processed images that are perceivable by our human vision systems. However, existing task-driven IQE models tend to overlook an underlying fact -- different levels of vision tasks have varying and sometimes conflicting requirements of image features. To address this problem, this paper proposes a generalized gradient promotion (GradProm) training strategy for task-driven IQE of medical images. Specifically, we partition a task-driven IQE system into two sub-models, i.e., a mainstream model for image enhancement and an auxiliary model for visual recognition. During training, GradProm updates only parameters of the image enhancement model using gradients of the visual recognition model and the image enhancement model, but only when gradients of these two sub-models are aligned in the same direction, which is measured by their cosine similarity. In case gradients of these two sub-models are not in the same direction, GradProm only uses the gradient of the image enhancement model to update its parameters. Theoretically, we have proved that the optimization direction of the image enhancement model will not be biased by the auxiliary visual recognition model under the implementation of GradProm. Empirically, extensive experimental results on four public yet challenging medical image datasets demonstrated the superior performance of GradProm over existing state-of-the-art methods.

cs.CV↗
arXiv2024

SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training

Existing text-to-image (T2I) diffusion models face several limitations, including large model sizes, slow runtime, and low-quality generation on mobile devices. This paper aims to address all of these challenges by developing an extremely small and fast T2I model that generates high-resolution and high-quality images on mobile platforms. We propose several techniques to achieve this goal. First, we systematically examine the design choices of the network architecture to reduce model parameters and latency, while ensuring high-quality generation. Second, to further improve generation quality, we employ cross-architecture knowledge distillation from a much larger model, using a multi-level approach to guide the training of our model from scratch. Third, we enable a few-step generation by integrating adversarial guidance with knowledge distillation. For the first time, our model SnapGen, demonstrates the generation of 1024x1024 px images on a mobile device around 1.4 seconds. On ImageNet-1K, our model, with only 372M parameters, achieves an FID of 2.06 for 256x256 px generation. On T2I benchmarks (i.e., GenEval and DPG-Bench), our model with merely 379M parameters, surpasses large-scale models with billions of parameters at a significantly smaller size (e.g., 7x smaller than SDXL, 14x smaller than IF-XL).

cs.CV↗
arXiv2024

EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation

While post-training compression techniques effectively reduce the memory footprint, latency, and power consumption of Large Language Models (LLMs), they often result in noticeable accuracy degradation and remain limited by hardware and kernel constraints that restrict supported compression formats - ultimately reducing flexibility across a wide range of deployment scenarios. In this work, we propose EoRA - a novel $\textbf{fine-tuning-free}$ method that augments compressed LLMs with low-rank matrices, allowing users to rapidly enhance task-specific performance and freely balance the trade-off between accuracy and computational overhead beyond the constraints of compression formats. EoRA consistently outperforms prior fine-tuning-free low rank methods in recovering the accuracy of compressed LLMs, achieving notable accuracy improvements (e.g., $\mathbf{10.84\%}$ on ARC-Challenge, $\mathbf{6.74\%}$ on MathQA, and $\mathbf{11.45\%}$ on GSM8K for LLaMA3-8B compressed to 3-bit). We also introduce an optimized CUDA kernel, accelerating inference by up to 1.4x and reducing memory overhead through quantizing EoRA. Overall, EoRA offers a prompt solution for improving the accuracy of compressed models under varying user requirements, enabling more efficient and flexible deployment of LLMs. Code is available at https://github.com/NVlabs/EoRA.

cs.CL↗