arXiv subjects

Wei Fang

Publications and source records attributed to Wei Fang.

At least 19 recordsLinked to original sources

arXiv2026

Adversarial Speculative Reasoning Improves Long Horizon Agents

Speculative decoding has been treated purely as a systems optimization that speeds up large language model decoding without changing the model behavior. Under this view, the growing effort to train better draft models has been focused solely on acceptance rate. We argue that this view does not hold true for long-horizon agent reasoning. Measuring frontier open-weight models on complex agentic tasks with different speculative decoding approaches, we found that numerical noise grows within verification windows, and the draft acceptance results of the thinking process can change the output distribution of the model after 30 steps, thus noticeably influencing the reasoning accuracy of long-horizon agents in random directions. In this work, we improve the reasoning capability of target models by controlling such noise. While we cannot change the overall token distribution verified by the target model, we can encode critical reasoning with highest precision by training the draft model to be rejected. We identify these points in agent traces and train the draft model to favor adversarial preference. At inference the trained draft and the target part ways precisely at these decision points, verification restarts, so that critical thinking tokens are sampled from the target model and encoded under its least noisy conditions. This approach makes critical reasoning better indexed and more durable over a long horizon. On complex agentic coding benchmarks, our approach raises end-to-end success rate with no change to the target model or its output distribution. Our results recast the speculative decoding mechanism from a pure accelerator into an active allocator for context precision that improves the accuracy of long-horizon agents by training 0.06% to 0.28% of hosted parameters.

cs.AI↗

arXiv2026

M3Former: Fine-Grained Cross-Layer Mixing for Transformers

Residual connections give each Transformer block access to all earlier layers only through one fixed sum, broadcast to all of the block's inputs. This broadcast bottleneck imposes three constraints: the query, key, value and residual inputs of a block, which we call its roles, read the same vector; all hidden dimensions within a role share one set of weights over earlier layers; and every earlier layer has the same fixed weight for every token. We propose the Multi-Role Multi-Group Mixing Residual (M3), which removes all three: every role, and every group of hidden dimensions within a role, reads its own token-dependent mixture of all earlier layers. M3 starts as an exact residual connection and adds as little as 1.4% parameters and 1.8% FLOPs. From 100M to 1.4B parameters, M3Former outperforms the Transformer and coarse-grained cross-layer connections at every size, matching a Transformer 1.19-1.34x the size of the one it modifies, trained with 1.4-1.8x the compute. Relaxing only some of the constraints recovers only part of this gain. M3Former also improves sparse mixture-of-experts models of up to 4.6B parameters and trains more stably in deeper networks. Code: https://github.com/Kingchet10/m3former

cs.LG↗

arXiv2026

Isotope Effects at Classical Cost through Mass-Differentiable Machine Learning

Isotope effects govern fractionation and modulate reactivity, with applications from hydrogen energy to environmental science and catalysis, yet predicting them requires resolving small isotope-dependent free-energy differences that remain very challenging for conventional path-integral simulations in complex systems. Here we introduce iso-EPIGS, a path-integral coarse-graining framework built on a mass-differentiable neural network that reconstructs the mass- and temperature-dependent path integral centroid free-energy surface. Classical molecular dynamics on the learned surface yields rigorous isotope-resolved thermodynamics without explicit path-integral sampling. Benchmarks spanning gas, liquid, and crystalline phases, including liquid water and oxalic acid crystal, reproduce reference path-integral isotope free-energy differences, enthalpies, and lattice parameters at near classical computational cost. Crucially, iso-EPIGS trained solely on all-H and all-D isotopologues retains high accuracy for unseen partially deuterated isotopologues, demonstrating robust transferability across nuclear masses. Iso-EPIGS makes accurate isotope-effect simulations feasible for complex systems and lays the groundwork for foundation models of isotope effects across chemical space.

physics.chem-ph↗

arXiv2026

Parallel Time-Aligned Spiking Self-Attention for Consistent Integer-Valued Training and Spike-Driven Inference

Integer-valued leaky integrate-and-fire (I-LIF) neurons and spike firing approximation (SFA) reduce temporal training cost by representing spike trains as firing counts and normalized firing rates, respectively. However, applying spiking self-attention (SSA) directly to these compressed query, key, and value representations introduces cross-time interactions that are absent during spike-driven inference. We term this operator-level discrepancy Temporal Interaction Mismatch (TIM). We propose Parallel Time-Aligned Spiking Self-Attention (PT-SSA), which reconstructs consecutive virtual spike slices from either I-LIF counts or SFA firing rates, computes attention only between time-aligned slices in parallel, and sums the per-step outputs. To accommodate the reduced attention output scale under SFA, we further introduce Adaptive PT-SSA, which learns a positive per-block rescaling before the output SFA neuron to improve firing-level utilization. Experiments on CIFAR-10, CIFAR-100, and ImageNet-1K show that the proposed methods substantially reduce train--inference mismatch. On CIFAR-100 with I-LIF, PT-SSA reduces the mean Top-1 gap from 1.85 to 0.29 percentage points. On ImageNet-1K, Adaptive PT-SSA reduces the Top-1 gap from 27.78 to 0.06 percentage points and achieves 74.53\% spike-driven Top-1 accuracy. A Triton-fused PT-SSA training kernel retains a $2.91\times$ throughput advantage over recurrent LIF SSA.

cs.NE↗

arXiv2026

In-Situ Quantum Optical Measurement for Colloidal Quantum Dots Confined in an Optical Trap

While optical manipulation of atomic arrays has reached a high degree of precision and scalability, the stable optical confinement of solution-based artificial atoms like colloidal quantum dots (CQDs) remains hindered by weak trapping forces and thermal fluctuations. High-intensity trapping often compromises the quantum properties of these emitters, creating a significant trade-off between mechanical stability and optical integrity. To overcome this, we propose encapsulating CQDs within a transparent polymer matrix, thereby increasing the effective interaction volume and optical restoring force without altering the emitters themselves. This strategy allows for stable spatial confinement under standard experimental conditions, as evidenced by the direct resolution of positional fluctuations through photoluminescence imaging and trajectory tracking. With averaged position fluctuations below 20 nm, the intrinsic emission spectra and photoluminescence decay dynamics remain largely unaffected, and photon-correlation measurements confirm the full preservation of single-photon emission. These findings establish a robust method for the controlled confinement of colloidal quantum emitters and in-situ quantum-optical measurements for future advancements in quantum-optical manipulation of artificial atoms.

physics.optics↗

arXiv2026

SeVeR: Selective Visual Exposure and Retrieval for 3D Medical Image Question Answering

Volumetric medical VQA requires reasoning over long and redundant 3D visual token sequences, especially in multi-sequence MRI where complementary modalities provide diverse diagnostic cues but expose the decoder to many repeated anatomical regions. To investigate reasoning under multi-sequence visual redundancy, we first introduce BreMRIs-VQA, a clinically curated breast MRI benchmark with 1.19M QA pairs from 71.0K sequences and 12.9K patients, covering both free-text and multiple-choice questions. We further propose SeVeR, a selective visual exposure framework that compresses dense volumes into modality-wise prototypes and retrieves complementary multi-level evidence with change-aware gated attention during decoding, trained with a marginal-utility self-consistency objective that suppresses unhelpful retrieval. Experiments on BreMRIs-VQA and public benchmarks show that SeVeR improves both discriminative and generative performance while exposing substantially fewer visual tokens.

cs.CV↗

arXiv2026

Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN Ticket

Spiking Neural Networks (SNNs), known for their biologically plausible architecture, face the challenge of limited performance. The self-attention mechanism, which is the cornerstone of the high-performance Transformer and also a biologically inspired structure, is absent in existing SNNs. To this end, we explore the potential of leveraging both self-attention capability and biological properties of SNNs, and propose a novel Spiking Self-Attention (SSA) and Spiking Transformer (Spikformer). The SSA mechanism eliminates the need for softmax and captures the sparse visual feature employing spike-based Query, Key, and Value. This sparse computation without multiplication makes SSA efficient and energy-saving. Further, we develop a Spiking Convolutional Stem (SCS) with supplementary convolutional layers to enhance the architecture of Spikformer. The Spikformer enhanced with the SCS is referred to as Spikformer V2. To train larger and deeper Spikformer V2, we introduce a pioneering exploration of Self-Supervised Learning (SSL) within the SNN. Specifically, we pre-train Spikformer V2 with masking and reconstruction style inspired by the mainstream self-supervised Transformer, and then finetune the Spikformer V2 on the image classification on ImageNet. Extensive experiments show that Spikformer V2 outperforms other previous surrogate training and ANN2SNN methods. An 8-layer Spikformer V2 achieves an accuracy of 80.38% using 4 time steps, and after SSL, a 172M 16-layer Spikformer V2 reaches an accuracy of 81.10% with just 1 time step. To the best of our knowledge, this is the first time that the SNN achieves 80+% accuracy on ImageNet. The code will be available at Spikformer V2.

cs.NE↗

arXiv2026

Efficiently Training Time-to-First-Spike Spiking Neural Networks from Scratch

Spiking Neural Networks (SNNs), with their event-driven and biologically inspired mechanisms, are well-suited for energy-efficient neuromorphic hardware. Neural coding, which is critical to SNNs, determines how information is represented via spikes. While Time-to-First-Spike (TTFS) coding uses a single spike per neuron to offer extreme sparsity and energy efficiency, it often suffers from unstable training and low accuracy due to its sparse firing. To address these challenges, we propose a training framework that incorporates parameter initialization, training normalization, a temporal output decoder, and a re-evaluation of the pooling layer. The proposed parameter initialization and training normalization mitigate signal diminishing and gradient vanishing, which helps stabilize training. Our output decoder aggregates temporal spikes to encourage earlier firing, thereby reducing latency. The re-evaluation of the pooling layer demonstrates that max-pooling violates single-spike constraints, which should be avoided, whereas average-pooling preserves them. Experiments show that our framework stabilizes and accelerates training, reduces latency, and achieves state-of-the-art accuracy for step-by-step TTFS SNNs on MNIST (99.48%), Fashion-MNIST (92.90%), CIFAR10 (90.56%), CIFAR100 (70.27%) and DVS Gesture (95.83%).

cs.NE↗

arXiv2026

Enhancing Photometric Redshift Estimation for LSST with a Hybrid LSTM-Mixture Density Network

Accurate photometric redshift (photo-$z$) estimation and robust uncertainty quantification are essential for the LSST to achieve its precision cosmology goals. Traditional machine learning algorithms are largely restricted to point estimates, struggling to characterize the multimodal nature of redshift PDFs and the degeneracies within the color-redshift space. To address this, we present and validate the LSTM-MDNz architecture, which integrates sequential feature extraction with flexible probability density modeling to enhance both prediction accuracy and uncertainty calibration across a broad redshift range, thereby meeting the stringent data quality requirements necessitated by next-generation cosmological analysis. The LSTM-MDNz framework treats multi-band photometry as wavelength-ordered sequences, utilizing LSTM networks to capture non-linear evolutionary correlations across the SED. A Mixture Density Network (MDN) is then employed to explicitly model posterior PDFs via Gaussian mixture models (GMMs). Performance is evaluated on the HSC GalaxiesML dataset (which serves as a small-scale proxy for next-generation surveys like LSST) and benchmarked against the BNN architecture established by Jones et al. (2024). The proposed model consistently outperforms the BNN baseline, achieving a $\sim 10\%$ improvement in point-estimation accuracy (specifically across RMSE, MAE, scatter, and $σ_{\text{NMAD}}$) and a $\sim 20\%$ reduction in the rates of both general and catastrophic outliers. A uniform probability integral transform (PIT) distribution confirms well-calibrated probabilistic outputs. Furthermore, the PDF-based confidence metric $z_{\text{conf}}$ enables high-purity catalog construction: excluding just approximately $4\%$ of extremely low-confidence ($z_{\text{conf}} < 0.05$) samples reduces the overall outlier rate by $\sim 48\%$.

astro-ph.GA↗

arXiv2026

BreastGPT: A Multimodal Large Language Model for the Full Spectrum of Breast Cancer Clinical Routine

Breast cancer remains a leading cause of cancer-related mortality among women. Its clinical management requires multimodal reasoning across a clinical workflow that spans \textit{screening}, \textit{diagnosis} and \textit{treatment planning}, where each stage involves distinct imaging modalities, task objectives, and reasoning patterns. However, constrained by data scarcity and model versatility, existing medical MLLMs are typically evaluated on isolated modalities or narrow task families, limiting their ability to support workflow-level clinical reasoning. In this work, we first introduce \textbf{BreastStage}, a workflow-aligned breast imaging instruction corpus comprising 1.86M instruction-following pairs curated from 17 sub-datasets across 5 imaging modalities and 136 task templates. Its held-out split, \textbf{BreastStage-Bench}, provides a comprehensive benchmark for evaluating multimodal reasoning across the breast cancer care continuum. Building on this corpus, we propose \textbf{BreastGPT}, a unified MLLM equipped with a dual-branch visual encoder and concept-preserving token compression to bridge the scale gap between standard radiology and gigapixel pathology. On BreastStage-Bench, BreastGPT achieves 75.66\% closed-ended accuracy and 89.92\% open-ended score, outperforming both general-purpose and medical-specific MLLMs across clinical stages and task formats. These results suggest that workflow-aligned data and cross-scale visual modeling are critical for clinically grounded medical MLLMs. All data, code, and model checkpoints are released at https://yangyy-liu.github.io/BreastGPT.io.

cs.CV↗

arXiv2026

Event2Vec: Processing Neuromorphic Events Directly by Representations in Vector Space

Neuromorphic event cameras possess superior temporal resolution, power efficiency, and dynamic range compared to traditional cameras. However, their asynchronous and sparse data format poses a significant challenge for conventional deep learning methods. Most existing methods either densify events into frames, sacrificing their sparse asynchronous nature, or use irregular models that are less compatible with GPU acceleration. Inspired by word-to-vector models, we propose event2vec, a novel representation that allows Transformers to process events directly. We demonstrate the effectiveness of event2vec on the DVS Gesture, ASL-DVS, and DVS-Lip benchmarks, showing that event2vec is remarkably parameter-efficient, features high throughput and low latency, and achieves high accuracy even with an extremely low number of events or low spatial resolutions. These results show that sparse asynchronous event data can be directly integrated into high-throughput Transformer architectures, offering an efficient paradigm for real-time neuromorphic vision. The code is provided at https://github.com/Intelligent-Computing-Lab-Panda/event2vec.

cs.CV↗

arXiv2026

Rigorous Quantum Thermodynamics from Entropic Path Integral Coarse-Graining

Nuclear quantum effects (NQEs) remain a major challenge for molecular simulations, as rigorous treatment requires imaginary-time path-integral methods with heavy computational overhead. Neglecting NQEs leads to systematic errors in thermodynamic properties and failures in predicting isotope effects, quantum tunnelling, and anharmonic zero-point motion. Here, we introduce entropic path-integral coarse-graining (EPIGS), which enables rigorous quantum thermodynamics at the cost of classical simulations by training size- and temperature-transferable effective potentials utilising absolute centroid free energy and entropy. Central to EPIGS is an instanton-based free-energy perturbation scheme that enables efficient and accurate evaluation of the centroid free energy and entropy for large systems, making construction of the EPIGS training dataset practical. Benchmarks against full path-integral simulations on representative hydrogen-bonded systems, including liquid water, show that EPIGS reproduces quantum free energies and enthalpies within 0.2 meV/atom at near-classical computational cost. EPIGS provides a highly accurate, scalable and low-cost framework for quantum thermodynamic simulations of complex systems across temperatures.

physics.chem-ph↗

arXiv2026

Quantum-Optically Resolving the Number of Colloidal Quantum Dots in a Subwavelength Volume

The number resolution of solid-state artificial atoms is of fundamental interest for the study of quantum few-body systems, yet remains experimentally challenging. Quantum optical experiments offer a non-invasive approach which links up macroscopic measurements with the quantity of quantum emitters. In this work, we propose a time-domain quantum optical methodology for the strict numbering of colloidal CdSe/CdS/ZnS quantum dots (QDs) confined in subwavelength-size polystyrene capsules. The non-polarized, homogeneously broadened emission of colloidal QDs in the subwavelength volume satisfies the description of Dicke's superradiance of identical quantum emitters. An analytic relation describes the numerical dependence of the second-order photon correlation on the number and the collective lifetime of emitters, yielding an experimental counting range of colloidal QDs from one to ten. This work provides a robust pathway for the non-invasive numbering of artificial atoms and the investigation of collective light-matter interactions at the nanoscale.

quant-ph↗

arXiv2026

Beyond Single-Shot: Multi-step Tool Retrieval via Query Planning

LLM agents operating over massive, dynamic tool libraries rely on effective retrieval, yet standard single-shot dense retrievers struggle with complex requests. These failures primarily stem from the disconnect between abstract user goals and technical documentation, and the limited capacity of fixed-size embeddings to model combinatorial tool compositions. To address these challenges, we propose TOOLQP, a lightweight framework that models retrieval as iterative query planning. Instead of single-shot matching, TOOLQP decomposes instructions into sub-tasks and dynamically generates queries to interact with the retriever, effectively bridging the semantic gap by targeting the specific sub-tasks required for composition. We train TOOLQP using synthetic query trajectories followed by optimization via Reinforcement Learning with Verifiable Rewards (RLVR). Experiments demonstrate that TOOLQP achieves state-of-the-art performance, exhibiting superior zero-shot generalization, robustness across diverse retrievers, and significant improvements in downstream agentic execution.

cs.CL↗

arXiv2025

Information-Scrambling-Enhanced Quantum Sensing Beyond the Standard Quantum Limit

Quantum sensing promises measurement precision beyond classical limits, but its practical realization is often hindered by decoherence and the challenges of generating and stabilizing entanglement in large-scale systems. Here, we experimentally demonstrate a scalable, scrambling-enhanced quantum sensing protocol, referred to as butterfly metrology, implemented on a cross-shaped superconducting quantum processor. By harnessing quantum information scrambling, the protocol converts local interactions into delocalized metrologically useful correlations, enabling robust signal amplification through interference of the scrambled and polarized quantum states. We validate the time-reversal ability via Loschmidt echo measurements and quantify the information scrambling through out-of-time-ordered correlators, establishing the essential quantum resources of our protocol. Our measurements reveal that the sensing sensitivity surpasses the standard quantum limit (SQL) with increasing qubit number, reaching 3.78 in a 9-qubit configuration, compared to the SQL of 3.0. The scheme further exhibits inherent robustness to coherent control errors and probed signal noise. This work demonstrates a readily scalable path toward practical quantum sensing advantages with prevalent experimental platforms.

quant-ph↗

arXiv2025

Scalable Dendritic Modeling Advances Expressive and Robust Deep Spiking Neural Networks

Dendritic computation endows biological neurons with rich nonlinear integration and high representational capacity, yet it is largely missing in existing deep spiking neural networks (SNNs). Although detailed multi-compartment models can capture dendritic computations, their high computational cost and limited flexibility make them impractical for deep learning. To combine the advantages of dendritic computation and deep network architectures for a powerful, flexible and efficient computational model, we propose the dendritic spiking neuron (DendSN). DendSN explicitly models dendritic morphology and nonlinear integration in a streamlined design, leading to substantially higher expressivity than point neurons and wide compatibility with modern deep SNN architectures. Leveraging the efficient formulation and high-performance Triton kernels, dendritic SNNs (DendSNNs) can be efficiently trained and easily scaled to deeper networks. Experiments show that DendSNNs consistently outperform conventional SNNs on classification tasks. Furthermore, inspired by dendritic modulation and synaptic clustering, we introduce the dendritic branch gating (DBG) algorithm for task-incremental learning, which effectively reduces inter-task interference. Additional evaluations show that DendSNNs exhibit superior robustness to noise and adversarial attacks, along with improved generalization in few-shot learning scenarios. Our work firstly demonstrates the possibility of training deep SNNs with multiple nonlinear dendritic branches, and comprehensively analyzes the impact of dendrite computation on representation learning across various machine learning settings, thereby offering a fresh perspective on advancing SNN design.

cs.NE↗

arXiv2025

Advancing Machine Learning Optimization of Chiral Photonic Metasurface: Comparative Study of Neural Network and Genetic Algorithm Approaches

Chiral photonic metasurfaces provide unique capabilities for tailoring light-matter interactions, which are essential for next-generation photonic devices. Here, we report an advanced optimization framework that combines deep learning and evolutionary algorithms to significantly improve both the design and performance of chiral photonic nanostructures. Building on previous work utilizing a three-layer perceptron reinforced learning and stochastic evolutionary algorithm with decaying changes and mass extinction for chiral photonic optimization, our study introduces a refined pipeline featuring a two-output neural network architecture to reduce the trade-off between high chiral dichroism (CD) and reflectivity. Additionally, we use an improved fitness function, and efficient data augmentation techniques. A comparative analysis between a neural network (NN)-based approach and a genetic algorithm (GA) is presented for structures of different interface pattern depth, material combinations, and geometric complexity. We demonstrate a twice higher CD and the impact of both the corner number and the refractive index contrast at the example of a GaP/air and PMMA/air metasurface as a result of superior optimization performance. Additionally, a substantial increase in the number of structures explored within limited computational resources is highlighted, with tailored spectral reflectivity suggested by our electromagnetic simulations, paving the way for chiral mirrors applicable to polarization-selective light-matter interaction studies.

physics.optics↗

arXiv2025

COMPARE: Clinical Optimization with Modular Planning and Assessment via RAG-Enhanced AI-OCT: Superior Decision Support for Percutaneous Coronary Intervention Compared to ChatGPT-5 and Junior Operators

Background: While intravascular imaging, particularly optical coherence tomography (OCT), improves percutaneous coronary intervention (PCI) outcomes, its interpretation is operator-dependent. General-purpose artificial intelligence (AI) shows promise but lacks domain-specific reliability. We evaluated the performance of CA-GPT, a novel large model deployed on an AI-OCT system, against that of the general-purpose ChatGPT-5 and junior physicians for OCT-guided PCI planning and assessment. Methods: In this single-center analysis of 96 patients who underwent OCT-guided PCI, the procedural decisions generated by the CA-GPT, ChatGPT-5, and junior physicians were compared with an expert-derived procedural record. Agreement was assessed using ten pre-specified metrics across pre-PCI and post-PCI phases. Results: For pre-PCI planning, CA-GPT demonstrated significantly higher median agreement scores (5[IQR 3.75-5]) compared to both ChatGPT-5 (3[2-4], P<0.001) and junior physicians (4[3-4], P<0.001). CA-GPT significantly outperformed ChatGPT-5 across all individual pre-PCI metrics and showed superior performance to junior physicians in stent diameter (90.3% vs. 72.2%, P<0.05) and length selection (80.6% vs. 52.8%, P<0.01). In post-PCI assessment, CA-GPT maintained excellent overall agreement (5[4.75-5]), significantly higher than both ChatGPT-5 (4[4-5], P<0.001) and junior physicians (5[4-5], P<0.05). Subgroup analysis confirmed CA-GPT's robust performance advantage in complex scenarios. Conclusion: The CA-GPT-based AI-OCT system achieved superior decision-making agreement versus a general-purpose large language model and junior physicians across both PCI planning and assessment phases. This approach provides a standardized and reliable method for intravascular imaging interpretation, demonstrating significant potential to augment operator expertise and optimize OCT-guided PCI.

cs.AI↗