“2026-03-16”版本间的差异
来自cslt Wiki
Duwenqiang（讨论 | 贡献） |
|||
| （6位用户的6个中间修订版本未显示） | |||
| 第44行： | 第44行： | ||
|Yang Wei | |Yang Wei | ||
|| | || | ||
| − | * | + | * Deal with streaming audio visual speech separation. |
|| | || | ||
* | * | ||
| 第66行： | 第66行： | ||
|Yue Gu | |Yue Gu | ||
|| | || | ||
| − | * | + | * still write my Phd paper |
|| | || | ||
* | * | ||
| 第89行： | 第89行： | ||
|Pengqi Li | |Pengqi Li | ||
|| | || | ||
| − | * | + | * Interview preparation |
| + | * Experimentation[https://z1et6d3xtb.feishu.cn/docx/U2ahdnEdbolPluxExxWcnmI3nog] | ||
|| | || | ||
* | * | ||
| 第111行： | 第112行： | ||
|Yu Zhang | |Yu Zhang | ||
|| | || | ||
| − | * | + | * GPU Util: [https://z1et6d3xtb.feishu.cn/wiki/XX4NwX3tJiBDcgkMi0hcFUtInHh] |
| + | * LLM: Swarm Lazy & Adv complex topo pruning finish (ECS for Adv Agents, PKS for Lazy Agents) | ||
|| | || | ||
* | * | ||
| 第122行： | 第124行： | ||
|Junhui Chen | |Junhui Chen | ||
|| | || | ||
| − | * | + | * Organizing existing experiments and structuring the logic; identified some issues in the experiments and arguments (currently a bit messy) and continuing to refine. |
|| | || | ||
* | * | ||
| 第157行： | 第159行： | ||
|Bochao Hu | |Bochao Hu | ||
|| | || | ||
| − | * | + | * finetuning visual encoder in new domain, which cer is 0.2727 |
| + | * baseline: VSR-pre-trained Encoder + Qwen_VL finetune only (VL-Decoder) is in training | ||
|| | || | ||
* | * | ||
| 第168行： | 第171行： | ||
|Hongcheng Zhang | |Hongcheng Zhang | ||
|| | || | ||
| − | * | + | *inhome data test，the report will finish on Tuesday |
| + | *read some paper | ||
|| | || | ||
* | * | ||
| 第179行： | 第183行： | ||
|Weiman Sun | |Weiman Sun | ||
|| | || | ||
| − | * | + | * debug the lora scripts of MTLLM |
| + | ** about 20w data records | ||
| + | ** takes about 34 hours to complete an epoch | ||
| + | * papers about speech instruction tune shared bay zhenghai and the TAC(Timestamped Audio Captioning) shared by hongcheng. | ||
|| | || | ||
| − | * | + | * |
|| | || | ||
* | * | ||
| 第187行： | 第194行： | ||
|Ge Gao | |Ge Gao | ||
|| | || | ||
| − | * | + | *cheak some AI courses translation |
| + | *read some papers about audio seperation | ||
|| | || | ||
* | * | ||
2026年3月16日 (一) 10:57的最后版本
| People | This Week | Next Week | Task Tracking (DeadLine) |
|---|---|---|---|
| Dong Wang |
|
|
|
| Lantian Li |
|
|
|
| Wenqiang Du |
|
|
|
| Yang Wei |
|
|
|
| Ying Shi |
|
|
|
| Yue Gu |
|
|
|
| Lily |
|
|
|
| Pengqi Li |
|
|
|
| Junming Yuan |
|
|
|
| Yu Zhang |
|
|
|
| Junhui Chen |
|
|
|
| Jiaying Wang |
|
|
|
| Xiaoxue Luo |
|
|
|
| Bochao Hu |
|
|
|
| Hongcheng Zhang |
|
|
|
| Weiman Sun |
|
|
|
| Ge Gao |
|
|
|
