Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Lei

Lei

50 indexed papers

Recent (6 mo)
50
With code
0
Influential cites
0
Benchmarked
0

Publications per year

50
26

Top categories

Vision×13Audio and Speech Processing×8AI×8NLP×7Robotics×6ML×5Sound×4Distributed×4

Frequent co-authors

Lei Xie5×
Lei Wang5×
Lei Yang4×
Lei Zhang3×
Fan Yang3×
Zhongang Cai2×

Research Timeline

2026
CW-Ghost: Search-Free Granularity Selection for Helper-Thread Prefetching via Capacity Windows

This paper introduces CW-Ghost, a method for estimating cache line fill volume and determining helper-thread prefetching granularity based on cache capacity constraints.

Argus: A General-Purpose Agentic Runtime for Long-Horizon Reasoning

Argus is a persistent, self-evolving runtime system that achieves better long-horizon reasoning results than Direct Copilot in seven GPT-5.5 benchmark arenas, with improvements in solve-input tokens, active workflow time, and verification-gated self-evolution.

TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories

This paper introduces TrajDebug, an error-lifecycle tracing framework for LLM-based agentic systems, which addresses long-trajectory error discovery using multi-granularity history compression and evidence-based error identification.

SemBridge: Semantic Token Anchoring for Continuous-Latent Autoregressive Speech Generation

This paper proposes SemBridge, a framework for continuous-latent autoregressive speech generation using discrete semantic tokens for supervision.

NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge

This paper reviews the NTIRE 2026 Low-light Enhancement competition, which merged misaligned smartphone images into a single, clean image in low-light conditions, achieving improvements of up to +6.49 dB in PSNR and +0.0101 in SSIM.

OpenCodeReview: Determinism over Non-Determinism for Cost-Effective Agent-Based Code Review

This paper introduces OpenCodeReview, a deterministic code review system that addresses non-determinism and context locality issues in LLM-based agents, achieving higher SEM-F1 scores and consuming fewer tokens.

GameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions

This paper introduces GameLogicBench, a benchmark for evaluating the ability of coding agents to implement gameplay rules in game development.

ForgetMimic: Motion Unlearning for Reinforcement Learning Humanoid Control

The paper proposes a method called ForgetMimic to eliminate specific motions from learned policies in humanoid control while preserving the effectiveness of other motions.

The Second MLC-SLM Challenge: Multilingual Conversational Speech Diarization, Recognition, and Understanding

The paper summarizes the Interspeech2026 Multilingual Conversational Speech Language Model Challenge and presents the results and insights from the challenge.

Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies

This paper introduces Grounded Entity Biographies (GEB), a long-video memory framework that groups visually grounded observations of the same physical instance across clips into retrievable biographies.

NeuroDyn-EEG: An Interpretable Pre-trained Model for EEG Based on Neural Dynamics

This paper proposes a pretraining framework called NeuroDyn-EEG that integrates generative priors from neural dynamics to estimate anatomically indexed physiological parameters from scalp EEG.

Compiling Together: High-Throughput Distributed Quantum Computing via Multi-Compilation

This paper improves the efficiency of distributed quantum computing by concurrently executing multiple compilations of the same quantum circuit.

MTEdit: Packed Trajectories Beat Rollouts for Multi-Turn Image Editing

The paper introduces MTEdit, a multi-turn image editing dataset and benchmark, to improve models' multi-turn image editing capabilities.

SkyAgent: Revisable Target Memory for Continuous Aerial Search

The paper presents a system called SkyAgent equipped with Revisable Target Memory (RTM) that improves continuous aerial search performance by revising and updating target hypotheses.

From Tasks to Turns: Measuring Human Labor Contributions in Human-Agent Joint Production

A framework for measuring human contributions in human-agent joint production is proposed.

RealComm: Benchmarking and Adapting Audio Deepfake Detection over Real Communication Channels

This paper introduces RealComm, a dataset and augmentation pipeline for evaluating the effects of real call transmission on audio deepfake detection.

Live Adaptation of Dataflow Stream Processing for Hybrid Edge-Cloud Analytics

This paper introduces Sluice, an adaptive data stream processing system for hybrid clouds, compatible with dataflow streaming engines.

Probing Spatial State Representations in Visual Foundation Models

This paper evaluates the spatial capabilities of visual foundation models through four levels of spatial capability and proposes a new evaluation framework.

Partial Interval Multicover Is NP-Complete Even for Unit Intervals

The authors prove that the unweighted decision problem of partial interval multicover is NP-complete even for unit intervals.

From Transcription to Reformulation: Defining and Benchmarking Grounded Generative Speech Recognition

The paper introduces Grounded Generative Speech Recognition (GSR), a reformulation of speech recognition as generating semantically grounded text instead of a single transcript.

Highlighted terms show continued research focus across papers

Papers

cs.DMTheoreticalRecentOct 30, 2026

Partial Interval Multicover Is NP-Complete Even for Unit Intervals

Mingchao Zhou, Yingli Ran, Lei Zhao, Xiangzhi Tu +1 more

The authors prove that the unweighted decision problem of partial interval multicover is NP-complete even for unit intervals.

View →
cs.CLcs.SDeess.ASEmpirical
Recent
Oct 30, 2026

From Transcription to Reformulation: Defining and Benchmarking Grounded Generative Speech Recognition

Qing Wang, Qihan Hu, Hang Lv, Yan Yang +8 more

The paper introduces Grounded Generative Speech Recognition (GSR), a reformulation of speech recognition as generating semantically grounded text instead of a single transcript.

View →
cs.CVcs.AIEmpiricalRecentOct 29, 2026

Probing Spatial State Representations in Visual Foundation Models

Baiqiao Yin, Zhongang Cai, Ruisi Wang, Qiwei Liang +2 more

This paper evaluates the spatial capabilities of visual foundation models through four levels of spatial capability and proposes a new evaluation framework.

View →
cs.DCEmpiricalRecentOct 26, 2026

Live Adaptation of Dataflow Stream Processing for Hybrid Edge-Cloud Analytics

Yuanli Wang, Prateek Jain, Lei Huang, Le Xu +1 more

This paper introduces Sluice, an adaptive data stream processing system for hybrid clouds, compatible with dataflow streaming engines.

View →
eess.ASEmpiricalRecentOct 20, 2026

RealComm: Benchmarking and Adapting Audio Deepfake Detection over Real Communication Channels

Li Wang, Jindong Wang, Wan Lin, Kunyu Feng +8 more

This paper introduces RealComm, a dataset and augmentation pipeline for evaluating the effects of real call transmission on audio deepfake detection.

View →
cs.HCEmpiricalRecentOct 19, 2026

From Tasks to Turns: Measuring Human Labor Contributions in Human-Agent Joint Production

Likai Wang, Dezhao Su, Jing Hu, Yunyun Wan +2 more

A framework for measuring human contributions in human-agent joint production is proposed.

View →
cs.CVEmpiricalRecentOct 16, 2026

MTEdit: Packed Trajectories Beat Rollouts for Multi-Turn Image Editing

Houyuan Chen, Fanzhou Wang, Xiangyu Fan, Songlin Yang +6 more

The paper introduces MTEdit, a multi-turn image editing dataset and benchmark, to improve models' multi-turn image editing capabilities.

View →
cs.ROEmpiricalRecentOct 16, 2026

SkyAgent: Revisable Target Memory for Continuous Aerial Search

Kaibo Yang, Xingyu Wu, Enze Zhu, Yajie Chai +5 more

The paper presents a system called SkyAgent equipped with Revisable Target Memory (RTM) that improves continuous aerial search performance by revising and updating target hypotheses.

View →
quant-phcs.AReess.SYEmpiricalRecentOct 2, 2026

Compiling Together: High-Throughput Distributed Quantum Computing via Multi-Compilation

Yipei Liu, Sen Zhang, Zebo Yang, Lei Yang

This paper improves the efficiency of distributed quantum computing by concurrently executing multiple compilations of the same quantum circuit.

View →
cs.CVcs.AIcs.CLEmpiricalRecentSep 29, 2026

Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies

Hui Ren, Lei Fan, Henry Pao, Han Guo +4 more

This paper introduces Grounded Entity Biographies (GEB), a long-video memory framework that groups visually grounded observations of the same physical instance across clips into retrievable biographie…

View →
cs.NEEmpiricalRecentSep 29, 2026

NeuroDyn-EEG: An Interpretable Pre-trained Model for EEG Based on Neural Dynamics

Yi Cui, Tong Zhao, Jiaxin Lei, Chuyi Yang +4 more

This paper proposes a pretraining framework called NeuroDyn-EEG that integrates generative priors from neural dynamics to estimate anatomically indexed physiological parameters from scalp EEG.

View →
cs.ROcs.CRcs.LGEmpiricalRecentSep 23, 2026

ForgetMimic: Motion Unlearning for Reinforcement Learning Humanoid Control

Xukun Luan, Zhongxiang Lei, Chen Gong, Shaowei Li +2 more

The paper proposes a method called ForgetMimic to eliminate specific motions from learned policies in humanoid control while preserving the effectiveness of other motions.

View →
eess.AScs.SDEmpiricalRecentSep 23, 2026

The Second MLC-SLM Challenge: Multilingual Conversational Speech Diarization, Recognition, and Understanding

Bingshen Mu, Mingchen Shao, Zhennan Lin, Liumeng Xue +6 more

The paper summarizes the Interspeech2026 Multilingual Conversational Speech Language Model Challenge and presents the results and insights from the challenge.

View →
cs.SEcs.AIcs.CLEmpiricalRecentSep 18, 2026

GameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions

Xinyu Che, Yunfei Ge, Shihao Li, Yanchen Liu +8 more

This paper introduces GameLogicBench, a benchmark for evaluating the ability of coding agents to implement gameplay rules in game development.

View →
cs.CVEmpiricalRecentAug 10, 2026

NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge

Aleksei Khalin, Egor Ershov, Artyom Panshin, Sergey Korchagin +45 more

This paper reviews the NTIRE 2026 Low-light Enhancement competition, which merged misaligned smartphone images into a single, clean image in low-light conditions, achieving improvements of up to +6.49…

View →
cs.SEEmpiricalRecentAug 10, 2026

OpenCodeReview: Determinism over Non-Determinism for Cost-Effective Agent-Based Code Review

Zhengfeng Li, Lei Zhang, Xianwei Wu, Zhengqi Zhuang +5 more

This paper introduces OpenCodeReview, a deterministic code review system that addresses non-determinism and context locality issues in LLM-based agents, achieving higher SEM-F1 scores and consuming fe…

View →
eess.AScs.SDEmpiricalRecentAug 7, 2026

SemBridge: Semantic Token Anchoring for Continuous-Latent Autoregressive Speech Generation

Hanke Xie, Haopeng Lin, Jiale Qian, Dake Guo +12 more

This paper proposes SemBridge, a framework for continuous-latent autoregressive speech generation using discrete semantic tokens for supervision.

View →
cs.AIEmpiricalRecentAug 6, 2026

TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories

Yunjia Qi, Zehua Yin, Xintong Shi, Hao Peng +9 more

This paper introduces TrajDebug, an error-lifecycle tracing framework for LLM-based agentic systems, which addresses long-trajectory error discovery using multi-granularity history compression and evi…

View →
cs.AIEmpiricalRecentAug 5, 2026

Argus: A General-Purpose Agentic Runtime for Long-Horizon Reasoning

Boxiu Li, Zimo Wen, Yijia Fan, Junxiang Lei +22 more

Argus is a persistent, self-evolving runtime system that achieves better long-horizon reasoning results than Direct Copilot in seven GPT-5.5 benchmark arenas, with improvements in solve-input tokens,…

View →
cs.DCEmpiricalRecentJul 28, 2026

CW-Ghost: Search-Free Granularity Selection for Helper-Thread Prefetching via Capacity Windows

Ya Zhang, Tong Lei, Yao Chen, Yonggang Che +3 more

This paper introduces CW-Ghost, a method for estimating cache line fill volume and determining helper-thread prefetching granularity based on cache capacity constraints.

View →