arXiv subjects

Feng Zhang

Publications and source records attributed to Feng Zhang.

At least 127 records · Page 7Linked to original sources

arXiv2025

Enhancing Robustness in Large Language Models: Prompting for Mitigating the Impact of Irrelevant Information

In recent years, Large language models (LLMs) have garnered significant attention due to their superior performance in complex reasoning tasks. However, recent studies may diminish their reasoning capabilities markedly when problem descriptions contain irrelevant information, even with the use of advanced prompting techniques. To further investigate this issue, a dataset of primary school mathematics problems containing irrelevant information, named GSMIR, was constructed. Testing prominent LLMs and prompting techniques on this dataset revealed that while LLMs can identify irrelevant information, they do not effectively mitigate the interference it causes once identified. A novel automatic construction method, ATF, which enhances the ability of LLMs to identify and self-mitigate the influence of irrelevant information, is proposed to address this shortcoming. This method operates in two steps: first, analysis of irrelevant information, followed by its filtering. The ATF method, as demonstrated by experimental results, significantly improves the reasoning performance of LLMs and prompting techniques, even in the presence of irrelevant information on the GSMIR dataset.

cs.CL↗

arXiv2025

MPS-Prover: Advancing Stepwise Theorem Proving by Multi-Perspective Search and Data Curation

Automated Theorem Proving (ATP) in formal languages remains a formidable challenge in AI, demanding rigorous logical deduction and navigating vast search spaces. While large language models (LLMs) have shown promising performance, existing stepwise provers often suffer from biased search guidance, leading to inefficiencies and suboptimal proof strategies. This paper introduces the Multi-Perspective Search Prover (MPS-Prover), a novel stepwise ATP system designed to overcome these limitations. MPS-Prover incorporates two key innovations: a highly effective post-training data curation strategy that prunes approximately 40% of redundant training data without sacrificing performance, and a multi-perspective tree search mechanism. This search integrates a learned critic model with strategically designed heuristic rules to diversify tactic selection, prevent getting trapped in unproductive states, and enhance search robustness. Extensive evaluations demonstrate that MPS-Prover achieves state-of-the-art performance on multiple challenging benchmarks, including miniF2F and ProofNet, outperforming prior 7B parameter models. Furthermore, our analyses reveal that MPS-Prover generates significantly shorter and more diverse proofs compared to existing stepwise and whole-proof methods, highlighting its efficiency and efficacy. Our work advances the capabilities of LLM-based formal reasoning and offers a robust framework and a comprehensive analysis for developing more powerful theorem provers.

cs.AI↗

arXiv2025

Seed1.5-VL Technical Report

We present Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning. Seed1.5-VL is composed with a 532M-parameter vision encoder and a Mixture-of-Experts (MoE) LLM of 20B active parameters. Despite its relatively compact architecture, it delivers strong performance across a wide spectrum of public VLM benchmarks and internal evaluation suites, achieving the state-of-the-art performance on 38 out of 60 public benchmarks. Moreover, in agent-centric tasks such as GUI control and gameplay, Seed1.5-VL outperforms leading multimodal systems, including OpenAI CUA and Claude 3.7. Beyond visual and video understanding, it also demonstrates strong reasoning abilities, making it particularly effective for multimodal reasoning challenges such as visual puzzles. We believe these capabilities will empower broader applications across diverse tasks. In this report, we mainly provide a comprehensive review of our experiences in building Seed1.5-VL across model design, data construction, and training at various stages, hoping that this report can inspire further research. Seed1.5-VL is now accessible at https://www.volcengine.com/ (Volcano Engine Model ID: doubao-1-5-thinking-vision-pro-250428)

cs.CV↗

arXiv2025

Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missions

Large language models (LLMs) demonstrate strong potential as agents for tool invocation due to their advanced comprehension and planning capabilities. Users increasingly rely on LLM-based agents to solve complex missions through iterative interactions. However, existing benchmarks predominantly access agents in single-mission scenarios, failing to capture real-world complexity. To bridge this gap, we propose the Multi-Mission Tool Bench. In the benchmark, each test case comprises multiple interrelated missions. This design requires agents to dynamically adapt to evolving demands. Moreover, the proposed benchmark explores all possible mission-switching patterns within a fixed mission number. Specifically, we propose a multi-agent data generation framework to construct the benchmark. We also propose a novel method to evaluate the accuracy and efficiency of agent decisions with dynamic decision trees. Experiments on diverse open-source and closed-source LLMs reveal critical factors influencing agent robustness and provide actionable insights to the tool invocation society.

cs.AI↗

arXiv2025

The Tenth NTIRE 2025 Image Denoising Challenge Report

This paper presents an overview of the NTIRE 2025 Image Denoising Challenge (σ = 50), highlighting the proposed methodologies and corresponding results. The primary objective is to develop a network architecture capable of achieving high-quality denoising performance, quantitatively evaluated using PSNR, without constraints on computational complexity or model size. The task assumes independent additive white Gaussian noise (AWGN) with a fixed noise level of 50. A total of 290 participants registered for the challenge, with 20 teams successfully submitting valid results, providing insights into the current state-of-the-art in image denoising.

cs.CV↗

arXiv2025

TXSQL: Lock Optimizations Towards High Contented Workloads (Extended Version)

Two-phase locking (2PL) is a fundamental and widely used concurrency control protocol. It regulates concurrent access to database data by following a specific sequence of acquiring and releasing locks during transaction execution, thereby ensuring transaction isolation. However, in strict 2PL, transactions must wait for conflicting transactions to commit and release their locks, which reduces concurrency and system throughput. We have observed this issue is exacerbated in high-contented workloads at Tencent, where lock contention can severely degrade system performance. While existing optimizations demonstrate some effectiveness in high-contention scenarios, their performance remains insufficient, as they suffer from lock contention and waiting in hotspot access. This paper presents optimizations in lock management implemented in Tencent's database, TXSQL, with a particular focus on high-contention scenarios. First, we discuss our motivations and the journey toward general lock optimization, which includes lightweight lock management, a copy-free active transaction list, and queue locking mechanisms that effectively enhance concurrency. Second, we introduce a hotspot-aware approach that enables certain highly conflicting transactions to switch to a group locking method, which groups conflicting transactions at a specific hotspot, allowing them to execute serially in an uncommitted state within a conflict group without the need for locking, thereby reducing lock contention. Our evaluation shows that under high-contented workloads, TXSQL achieves performance improvements of up to 6.5x and up to 22.3x compared to state-of-the-art methods and systems, respectively.

cs.DB↗

arXiv2025

Two-dimensional atomic-scale ultrathin lateral heterostructures

Ultrathin lateral heterostructures of monolayer MoS2 and WS2 have successfully been realized with the metal-organic chemical vapor deposition method. Atomic-resolution HAADF-STEM observations have revealed that the junction widths of lateral heterostructures range from several nanometers to single-atom thickness, the thinnest heterojunction in theory. The interfaces are atomically flat with minimal mixing between MoS2 and WS2, originating from rapid and abrupt switching of the source supply. Due to one-dimensional interfaces and broken rotational symmetry, the resulting ultrathin lateral heterostructures, 1~2 mixed-dimensional structures, can show emergent optical/electronic properties. The MOCVD growth developed in this work allows us to access various ultrathin lateral heterostructures, leading to future exploration of their emergent properties absent in each component alone.

cond-mat.mtrl-sci↗

arXiv2025

Adaptive variational quantum dynamics simulations with compressed circuits and fewer measurements

The adaptive variational quantum dynamics simulation (AVQDS) method performs real-time evolution of quantum states using automatically generated parameterized quantum circuits that often contain substantially fewer gates than Trotter circuits. Here we report an improved version of the method, which we call AVQDS(T), by porting the Tiling Efficient Trial Circuits with Rotations Implemented Simultaneously (TETRIS) technique. The algorithm adaptively adds layers of disjoint unitary gates to the ansatz circuit so as to keep the McLachlan distance, a measure of the accuracy of the variational dynamics, below a fixed threshold. We perform benchmark noiseless AVQDS(T) simulations of quench dynamics in local spin models demonstrating that the TETRIS technique significantly reduces the circuit depth and two-qubit gate count. We also show a method based on eigenvalue truncation to solve the linear equations of motion for the variational parameters with enhanced noise resilience. Finally, we propose a way to substantially alleviate the measurement overhead of AVQDS(T) while maintaining high accuracy by synergistically integrating quantum circuit calculations on quantum processing units with classical calculations using, e.g., tensor networks to evaluate the quantum geometric tensor. We showcase that this approach enables AVQDS(T) to deliver more accurate results than simulations using a fixed ansatz of comparable final depth for a significant time duration with fewer quantum resources.

quant-ph↗

arXiv2025

Towards Superior Quantization Accuracy: A Layer-sensitive Approach

Large Vision and Language Models have exhibited remarkable human-like intelligence in tasks such as natural language comprehension, problem-solving, logical reasoning, and knowledge retrieval. However, training and serving these models require substantial computational resources, posing a significant barrier to their widespread application and further research. To mitigate this challenge, various model compression techniques have been developed to reduce computational requirements. Nevertheless, existing methods often employ uniform quantization configurations, failing to account for the varying difficulties across different layers in quantizing large neural network models. This paper tackles this issue by leveraging layer-sensitivity features, such as activation sensitivity and weight distribution Kurtosis, to identify layers that are challenging to quantize accurately and allocate additional memory budget. The proposed methods, named SensiBoost and KurtBoost, respectively, demonstrate notable improvement in quantization accuracy, achieving up to 9% lower perplexity with only a 2% increase in memory budget on LLama models compared to the baseline.

cs.LG↗

arXiv2025

Inverse scattering transform for the focusing two-component Hirota equation with nonzero boundary conditions

Applying the inverse scattering transform to study a focusing two-component Hirota equation with nonzero boundary conditions at infinity. Through the spectral problem and the adjoint spectral problem, the analyticity properties and symmetry relations of the eigenfunctions and scattering coefficients are systematically investigated. Based on these properties, the discrete spectrum is comprehensively characterized, producing three types of discrete eigenvalues. The asymptotic behavior of the eigenfunctions and scattering coefficients is explored in detail. Furthermore, the inverse scattering problem is formulated through a suitable matrix Riemann-Hilbert problem, and the trace formula along with the reconstruction formula for the potential function are derived. The reflectionless condition facilitates the successful construction of N-soliton solution. Finally, various types of solitons are obtained by considering different types of discrete eigenvalues and their combinations, and the interactions of these solitons are demonstrated.

nlin.SI↗

arXiv2025

AdaF^2M^2: Comprehensive Learning and Responsive Leveraging Features in Recommendation System

Feature modeling, which involves feature representation learning and leveraging, plays an essential role in industrial recommendation systems. However, the data distribution in real-world applications usually follows a highly skewed long-tail pattern due to the popularity bias, which easily leads to over-reliance on ID-based features, such as user/item IDs and ID sequences of interactions. Such over-reliance makes it hard for models to learn features comprehensively, especially for those non-ID meta features, e.g., user/item characteristics. Further, it limits the feature leveraging ability in models, getting less generalized and more susceptible to data noise. Previous studies on feature modeling focus on feature extraction and interaction, hardly noticing the problems brought about by the long-tail data distribution. To achieve better feature representation learning and leveraging on real-world data, we propose a model-agnostic framework AdaF^2M^2, short for Adaptive Feature Modeling with Feature Mask. The feature-mask mechanism helps comprehensive feature learning via multi-forward training with augmented samples, while the adapter applies adaptive weights on features responsive to different user/item states. By arming base models with AdaF^2M^2, we conduct online A/B tests on multiple recommendation scenarios, obtaining +1.37% and +1.89% cumulative improvements on user active days and app duration respectively. Besides, the extended offline experiments on different models show improvements as well. AdaF$^2$M$^2$ has been widely deployed on both retrieval and ranking tasks in multiple applications of Douyin Group, indicating its superior effectiveness and universality.

cs.IR↗

arXiv2025

Long-Term Interest Clock: Fine-Grained Time Perception in Streaming Recommendation System

User interests manifest a dynamic pattern within the course of a day, e.g., a user usually favors soft music at 8 a.m. but may turn to ambient music at 10 p.m. To model dynamic interests in a day, hour embedding is widely used in traditional daily-trained industrial recommendation systems. However, its discreteness can cause periodical online patterns and instability in recent streaming recommendation systems. Recently, Interest Clock has achieved remarkable performance in streaming recommendation systems. Nevertheless, it models users' dynamic interests in a coarse-grained manner, merely encoding users' discrete interests of 24 hours from short-term behaviors. In this paper, we propose a fine-grained method for perceiving time information for streaming recommendation systems, named Long-term Interest Clock (LIC). The key idea of LIC is adaptively calculating current user interests by taking into consideration the relevance of long-term behaviors around current time (e.g., 8 a.m.) given a candidate item. LIC consists of two modules: (1) Clock-GSU retrieves a sub-sequence by searching through long-term behaviors, using query information from a candidate item and current time, (2) Clock-ESU employs a time-gap-aware attention mechanism to aggregate sub-sequence with the candidate item. With Clock-GSU and Clock-ESU, LIC is capable of capturing users' dynamic fine-grained interests from long-term behaviors. We conduct online A/B tests, obtaining +0.122% improvements on user active days. Besides, the extended offline experiments show improvements as well. Long-term Interest Clock has been integrated into Douyin Music App's recommendation system.

cs.IR↗

arXiv2025

Real-time Indexing for Large-scale Recommendation by Streaming Vector Quantization Retriever

Retrievers, which form one of the most important recommendation stages, are responsible for efficiently selecting possible positive samples to the later stages under strict latency limitations. Because of this, large-scale systems always rely on approximate calculations and indexes to roughly shrink candidate scale, with a simple ranking model. Considering simple models lack the ability to produce precise predictions, most of the existing methods mainly focus on incorporating complicated ranking models. However, another fundamental problem of index effectiveness remains unresolved, which also bottlenecks complication. In this paper, we propose a novel index structure: streaming Vector Quantization model, as a new generation of retrieval paradigm. Streaming VQ attaches items with indexes in real time, granting it immediacy. Moreover, through meticulous verification of possible variants, it achieves additional benefits like index balancing and reparability, enabling it to support complicated ranking models as existing approaches. As a lightweight and implementation-friendly architecture, streaming VQ has been deployed and replaced all major retrievers in Douyin and Douyin Lite, resulting in remarkable user engagement gain.

cs.IR↗

arXiv2025

Robust Low-Light Human Pose Estimation through Illumination-Texture Modulation

As critical visual details become obscured, the low visibility and high ISO noise in extremely low-light images pose a significant challenge to human pose estimation. Current methods fail to provide high-quality representations due to reliance on pixel-level enhancements that compromise semantics and the inability to effectively handle extreme low-light conditions for robust feature learning. In this work, we propose a frequency-based framework for low-light human pose estimation, rooted in the "divide-and-conquer" principle. Instead of uniformly enhancing the entire image, our method focuses on task-relevant information. By applying dynamic illumination correction to the low-frequency components and low-rank denoising to the high-frequency components, we effectively enhance both the semantic and texture information essential for accurate pose estimation. As a result, this targeted enhancement method results in robust, high-quality representations, significantly improving pose estimation performance. Extensive experiments demonstrating its superiority over state-of-the-art methods in various challenging low-light scenarios.

cs.CV↗

arXiv2025

AgentPose: Progressive Distribution Alignment via Feature Agent for Human Pose Distillation

Pose distillation is widely adopted to reduce model size in human pose estimation. However, existing methods primarily emphasize the transfer of teacher knowledge while often neglecting the performance degradation resulted from the curse of capacity gap between teacher and student. To address this issue, we propose AgentPose, a novel pose distillation method that integrates a feature agent to model the distribution of teacher features and progressively aligns the distribution of student features with that of the teacher feature, effectively overcoming the capacity gap and enhancing the ability of knowledge transfer. Our comprehensive experiments conducted on the COCO dataset substantiate the effectiveness of our method in knowledge transfer, particularly in scenarios with a high capacity gap.

cs.CV↗

arXiv2024

Prolonging Carrier Lifetime in P-type 4H-SiC Epilayer by Thermal Oxidation and Hydrogen Annealing

A minority carrier lifetime of 25.46 $μ$s in a P-type 4H-SiC epilayer has been attained through sequential thermal oxidation and hydrogen annealing. Thermal oxidation can enhance the minority carrier lifetime in the 4H-SiC epilayer by reducing carbon vacancies. However, this process also generates carbon clusters with limited diffusivity and contributes to the enlargement of surface pits on the 4H-SiC. High-temperature hydrogen annealing effectively reduces stacking fault and dislocation density. Moreover, electron spin resonance analysis indicates a significant reduction in carbon vacancy defects after hydrogen annealing. The mechanisms of the elimination of carbon vacancies by hydrogen annealing include the decomposition of carbon clusters formed during thermal oxidation and the low-pressure selective etching by hydrogen, which increases the carbon content on the 4H-SiC surface and facilitates carbon diffusion. Consequently, the combination of thermal oxidation and hydrogen annealing eliminates carbon vacancies more effectively, substantially enhancing the minority carrier lifetime in P-type 4H-SiC. This improvement is advantageous for the application of high-voltage SiC bipolar devices.

cond-mat.mtrl-sci↗

arXiv2024

Local Avalanche Photodetectors Driven by Lightning-rod Effect and Surface Plasmon Excitations

Sensitive avalanche photodetectors (APDs) that operate within the ultraviolet spectrum are critically required for applications in detecting fire and deep-space exploration. However, the development of such devices faces significant challenges, including high avalanche breakdown voltage, the necessity for complex quenching circuits, and thermal runaway associated with Geiger-mode avalanche operation. To mitigate these issues, we report on a 4H-SiC APD design utilizing micro-holes (MHs) structures and Al nano-triangles (NTs) to enhance surface electric field driven by strong localized surface plasmon excitations and lightning-rod effect. The device demonstrates a record low avalanche breakdown voltage of approximately 14.5 V, a high detectivity of 7E13 Jones, a nanosecond-level response time, and repeated stable detections without the requirement of a quenching circuit. Collectively, when compared with the conventional wide-bandgap-based APDs, this device achieves a reduction in avalanche breakdown voltage by an order of magnitude and exhibits a substantial increase in detectivity. Consequently, the proposed APD configuration presents a promising candidate for ultraviolet detection and integrated optoelectronic circuits.

physics.optics↗

arXiv2024

A Light-Emitting-Diodes-Integrated Silicon Carbide Insulated Gate Bipolar Transistor

A light-emitting-diodes (LEDs)-integrated silicon carbide (SiC) insulated gate bipolar transistors (LI-IGBT) is proposed in this paper. The novelty of the LI-IGBT depends on the photogeneration effect of III-nitride LEDs embedded in the poly-Si regions of IGBT. Then, the photogenerated carriers are formed in the JFET region and the drift layer, indicating the increase of the conductivity in LI-IGBT as compared with the SiC IGBT with hole-barrier layer (H-IGBT) and the SiC IGBT with charge storage layer (CSL-IGBT). The static simulation results show that the electron density of the LI-IGBT at the middle of the drift layer is separately 17.44 times and 15.81 times higher than those of the H-IGBT and CSL-IGBT, yielding 40.91% and 37.38% reduction of forward voltage drop, respectively, and also, the LI-IGBT shows 304.59% and 263.67% improvements in BFOM as compared with CSL-IGBT and H-IGBT, respectively. For the dynamic simulation in one cycle, the loss of LI-IGBT is separately reduced by 6.57% and 8.57% compared to H-IGBT and CSL-IGBT. Meanwhile, the relationship between VC(sat) and Eturn-off can be optimized by adjusting collector doping and minority carrier lifetime. These results reveal that the proposed SiC IGBT will be more suitable for ultra-high voltage application.

physics.app-ph↗