Xiaoran Fan

FeelWave: Enabling Emotion-Aware Voice Interaction through Noise-Robust mmWave Emotion Sensing

Wang Lingyu, You Zuo, Dequan Wang, Chenming He et autres

Voice has been a primary interaction mode with LLM-powered assistants. Beyond semantics, voice carries emotional cues with potential to guide empathetic system responses. Yet, robust vocal emotion sensing in noise and its use in optimizing interactions remain underexplored. In response, we present …

cn, us (code pays fourni par la source)

Needle in a Haystack: Tracking UAVs from Massive Noise in Real-World 5G-A Base Station Data

Chengzhen Meng, Chenming He, Yidong Jiang, Xiaoran Fan et autres

The potential usage of UAVs in daily life has made monitoring them essential. However, existing systems for monitoring UAVs typically rely on cameras, LiDARs, or radars, whose limited sensing range or high deployment cost hinder large-scale adoption. In response, we develop BSense, …

MHA2MLA-VLM: Enabling DeepSeek’s Economical Multi-Head Latent Attention Across Vision-Language Models

Xiaoran Fan, Zhichao Sun, Tao Ji, Lixing Shen et autres

As vision-language models (VLMs) tackle increasingly complex and multimodal tasks, the rapid growth of Key-Value (KV) cache imposes significant memory and computational bottlenecks during inference. While Multi-Head Latent Attention (MLA) offers an effective means to compress the KV cache and accelerate inference, …

Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination

Mingqi Wu, Zeyu Zhang, Qiaole Dong, Zhiheng Xi et autres

Reasoning in large language models has long been a central research focus, and recent studies employing reinforcement learning (RL) have introduced diverse methods that yield substantial performance gains with minimal or even no external supervision. Surprisingly, some studies even suggest that random …

cn, us (code pays fourni par la source)

Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment

Yuming Yang, Mingyoung Lai, Wanxu Zhao, Xiaoran Fan et autres

Long chain-of-thought (CoT) trajectories provide rich supervision signals for distilling reasoning from teacher to student LLMs. However, both prior work and our experiments show that trajectories from stronger teachers do not necessarily yield better students, highlighting the importance of data-student suitability in …

Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment

Yuming Yang, Mingyoung Lai, Wanxu Zhao, Xiaoran Fan et autres

Long chain-of-thought (CoT) trajectories provide rich supervision signals for distilling reasoning from teacher to student LLMs. However, both prior work and our experiments show that trajectories from stronger teachers do not necessarily yield better students, highlighting the importance of data-student suitability in …

cn, ca, au (code pays fourni par la source)

MHA2MLA-VLM: Enabling DeepSeek's Economical Multi-Head Latent Attention across Vision-Language Models

Xiaoran Fan, Zhichao Sun, Tao Ji, Lixing Shen et autres

As vision-language models (VLMs) tackle increasingly complex and multimodal tasks, the rapid growth of Key-Value (KV) cache imposes significant memory and computational bottlenecks during inference. While Multi-Head Latent Attention (MLA) offers an effective means to compress the KV cache and accelerate inference, …

MHA2MLA-VLM: Enabling DeepSeek's Economical Multi-Head Latent Attention across Vision-Language Models

Xiaoran Fan, Zhichao Sun, Tao Ji, Lixing Shen et autres

As vision-language models (VLMs) tackle increasingly complex and multimodal tasks, the rapid growth of Key-Value (KV) cache imposes significant memory and computational bottlenecks during inference. While Multi-Head Latent Attention (MLA) offers an effective means to compress the KV cache and accelerate inference, …

Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments

J. Ye, Changhao Jiang, Zhengyin Du, Yufei Xu et autres

Junjie Ye, Changhao Jiang, Zhengyin Du, Yufei Xu, Xuesong Yao, Zhiheng Xi, Xiaoran Fan, Qi Zhang, Tao Gui, Xuanjing Huang, Jiecao Chen. Findings of the Association for Computational Linguistics: ACL 2026. 2026.

cn (code pays fourni par la source)

mmMUSE: An mmWave-based Motion-resilient Universal Speech Enhancement System

Wang Lingyu, Dequan Wang, You Zuo, Chenming He et autres

Speech enhancement improves the user interaction experience in voice-based smart systems. While microphone-based speech perception is limited by airborne noise, mmWave is immune to such interference. However, user-device motion hinders mmWave-based vocal extraction, dispersing vocal signals and introducing distortions. In this paper, …

cn, us (code pays fourni par la source)

Ghost Points Matter: Far-Range Vehicle Detection with a Single mmWave Radar in Tunnel

Chenming He, Chengzhen Meng, Xiaoran Fan, Dequan Wang et autres

Vehicle detection in tunnels is crucial for traffic monitoring and accident response, yet remains underexplored. In this paper, we develop mmTunnel, a millimeter-wave radar system that achieves far-range vehicle detection in tunnels. The main challenge here is coping with ghost points caused …

cn, us (code pays fourni par la source)

Heart Rate Monitoring Through ANC Headphones in Unconstrained Environments

Zhenyu Wu, Maanya Shanker, Tao Chen, Xiaoran Fan et autres

This paper introduces CLEAR-APG, a novel acoustic sensing approach that enables reliable heart rate monitoring in unconstrained environments using off-the-shelf active noise cancellation (ANC) headphones. By emitting ultrasonic signals into the user's ear canal via the headphone speaker and analyzing their echoes, …

us (code pays fourni par la source)