“2026-03-09”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
 
（8位用户的11个中间修订版本未显示）
第29行： 第29行：
 
|Wenqiang Du
 
|Wenqiang Du
 
||
 
||
−
*
+
* Online KWS Model Debug for AIbabel
 
||
 
||
 
*
 
*
第40行： 第40行：
 
|Yang Wei
 
|Yang Wei
 
||
 
||
−
*
+
* Developing Audio visual speech separation streaming demo.
 
||
 
||
 
*
 
*
第106行： 第106行：
 
|Yu Zhang
 
|Yu Zhang
 
||
 
||
−
*
+
* GPU Util: [https://z1et6d3xtb.feishu.cn/wiki/XX4NwX3tJiBDcgkMi0hcFUtInHh]
 +
* LLM: Still Tuning the complex topo loss design (to prune Lazy Agents), find some bugs in loss design with @chenjunhui
 
||
 
||
 
*
 
*
第117行： 第118行：
 
|Junhui Chen
 
|Junhui Chen
 
||
 
||
−
*
+
* LLM
 +
** check @ZhangYu's code and debug
 +
** design a game to prove best swarm construction has highest parameter knowledge score (can be used in RL)
 
||
 
||
 
*
 
*
第127行： 第130行：
 
|-
 
|-
 
|Jiaying Wang
 
|Jiaying Wang
 +
||
 +
* Thesis modifying
 
||
 
||
 
*
 
*
 +
||
 +
*
 +
|-
 +
 +
 +
|-
 +
|Xiaoxue Luo
 +
||
 +
* attractor-based USS
 +
** filter out a purer dataset for training(use a SED model to detect the anchor segment in audio clip that is most likely contain a sound event)
 +
* Huawei project
 +
** train the model using VGGSound and data provided by Huawei(in training)
 +
*** 30epoch & 2mix: speech_sisdr = 11.785，music_sisdr = 11.7161. The previous training did have an overfitting problem.
 
||
 
||
 
*
 
*
第139行： 第157行：
 
|Bochao Hu
 
|Bochao Hu
 
||
 
||
−
*
+
* CNVSRC.topics dataset pipeline completed and process 1000 data samples for training and testing
 
||
 
||
 
*
 
*
第150行： 第168行：
 
|Hongcheng Zhang
 
|Hongcheng Zhang
 
||
 
||
−
*
+
*Evaluating the boundaries of visual capabilities for small and medium-sized models in Qwen3.5
 
||
 
||
 
*
 
*
第161行： 第179行：
 
|Weiman Sun
 
|Weiman Sun
 
||
 
||
−
*
+
* papers about the representation analysis to multi-task and instruction-tune
 +
* add the prompt-aware lora module to the MTLLM
 
||
 
||
 
*
 
*

2026年3月9日 (一) 10:56的最后版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • Keep on two NMI papers
Lantian Li
Wenqiang Du
  • Online KWS Model Debug for AIbabel
Yang Wei
  • Developing Audio visual speech separation streaming demo.
Ying Shi
  • thesis
Yue Gu
Lily
  • Thesis writing
Pengqi Li
Junming Yuan
Yu Zhang
  • GPU Util: [1]
  • LLM: Still Tuning the complex topo loss design (to prune Lazy Agents), find some bugs in loss design with @chenjunhui
Junhui Chen
  • LLM
    • check @ZhangYu's code and debug
    • design a game to prove best swarm construction has highest parameter knowledge score (can be used in RL)
Jiaying Wang
  • Thesis modifying
Xiaoxue Luo
  • attractor-based USS
    • filter out a purer dataset for training(use a SED model to detect the anchor segment in audio clip that is most likely contain a sound event)
  • Huawei project
    • train the model using VGGSound and data provided by Huawei(in training)
      • 30epoch & 2mix: speech_sisdr = 11.785，music_sisdr = 11.7161. The previous training did have an overfitting problem.
Bochao Hu
  • CNVSRC.topics dataset pipeline completed and process 1000 data samples for training and testing
Hongcheng Zhang
  • Evaluating the boundaries of visual capabilities for small and medium-sized models in Qwen3.5
Weiman Sun
  • papers about the representation analysis to multi-task and instruction-tune
  • add the prompt-aware lora module to the MTLLM
取自“http://cslt.org/mediawiki/index.php?title=2026-03-09&oldid=43971”