cslt Wiki - 用户贡献 [zh-cn]

2026-04-27

2026-04-27T10:54:35Z

Sunweiman：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||

* Check response for 16 AI textbooks
* Recheck micromagentics paper

||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
* Spech separation task
** add some loss to reduce leakage problem
* Baseline evaluation for audio event tasks
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Yue Gu
||
* write my phd thesis and revise one chapter
||
*
||
*
|-

|-
|Lily
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
* Continued the revision of the paper submitted to Journal of Chinese Information Processing
||
*
||
*
|-

|-
|Junming Yuan
||
* journal paper refinement(done and submit)
* prepare ICASSP oral presentation(done)
||
*
||
*
|-

|-
|Yu Zhang
||
* GPU Util: [https://z1et6d3xtb.feishu.cn/wiki/XX4NwX3tJiBDcgkMi0hcFUtInHh]
* Paper:
** Finish all lazy bubble prune accuracy & token consumption test
** Refine paper with @chenjunhui
* GAIA test (real word ToT MAS pipeline with function calling RAG)
** original ACC: 11 / 52
** ACC without all WebSearch: 8 / 52 (mostly are questions that can be solved by FileAnalyze or without any additional information)
** ACC without WebSearch that seg-ECS < 0.4: 11 / 52
** ACC without WebSearch that seg-ECS > 0.4: 8 / 52
||
*
||
*
|-

|-
|Junhui Chen
||
* still sick
* continue to refining the paper, and looking for references (80%)
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* retrain the USS-eda model using the data and training configuration from the SJTU 's paper
* train 2-3mix USS-tda model to compare the separation results with USS-eda(in training)
||
*
||
*
|-

|-
|Bochao Hu
||
*
||
*
||
*
|-

|-
|Hongcheng Zhang
||
*
||
*
||
*
|-

|-
|Weiman Sun
||
* test Qwen models and write report
* write graduation thesis
||
*
||
*
|-
|Ge Gao
||
*experiments on audio separation and prepared ball data
*wrote my graduation thesis
||
*
||
*
|-
|-
|Shuailong Li
||
*Test on Teacher Wei's dataset
*completed my graduation project UI and wrote the corresponding documentation.
*Reproduction on the MTASS original dataset（loss：MSE+SI-SDR）
**SDRi（speech=6.95 music=4.63 others=4.50 avg=5.43）
**The perceived volume has not decreased

||
*
||
*
|-

2026-04-20

2026-04-20T10:32:04Z

Sunweiman：

2026-04-13

2026-04-13T10:47:10Z

Sunweiman：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* FgW daily work
* MLA book (3/4)
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* revise my thesis
||
*
||
*
|-

|-
|Yue Gu
||
* write my Phd thesis
||
*
||
*
|-

|-
|Lily
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
* Paper Draft Completion & Revision Plan
||
*
||
*
|-

|-
|Junming Yuan
||
* Preparing the materials for attending ICASSP
* ZH paper draft (need refine)
||
*
||
*
|-

|-
|Yu Zhang
||
* GPU Util: [https://z1et6d3xtb.feishu.cn/wiki/XX4NwX3tJiBDcgkMi0hcFUtInHh]
* Chain level experiments:
** After introducing the Metric Reward, the weights of correct edges converge faster compared to training with pure reinforcement learning alone.
** The worse the situation when the Metric Reward is introduced (i.e., the lower the weights of critical edges), the more significant the difference compared to not using the Metric Reward.
||
*
||
*
|-

|-
|Junhui Chen
||
* To strengthen the robustness of the conclusions, conducting additional experiments:
** Introduce a new baseline (AgentPrune).
** Add experiments on a new dataset (GSM8K).
** Reproduce the results on other LLM base models.
* Paper writing
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* attractor visualization analysis [https://z1et6d3xtb.feishu.cn/docx/BAoRdM2jQo19krxwH0pcowCsnih]
* The accuracy of attractor counting is lower than expected, may be due to the mixed scenes are complex（2-5mix), retrain the 2-3mix model
||
*
||
*
|-

|-
|Bochao Hu
||
*
||
*
||
*
|-

|-
|Hongcheng Zhang
||
*
||
*
||
*
|-

|-
|Weiman Sun
||
* supplement our audioset dataset for specific classes
* test large multimodal models
||
*
||
*
|-
|Ge Gao
||
*reproduce spatialnet for speech separation
*write my graduation thesis
||
*
||
*
|-
|-
|Shuailong Li
||
*read some papers
**USE（Sepformer and BSRNN and TDN）
||
*
||
*
|-

2026-03-30

2026-03-30T10:14:16Z

Sunweiman：

2026-03-23

2026-03-30T10:08:00Z

Sunweiman：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* AIGE book (University version 1/4)
* Keep on NMI paper proof editing

||
*
||
*
|-

|-
|Lantian Li
||
* MoE daily work
||
*
||
*
|-

|-
|Wenqiang Du
||
*AIbabel
** Deployment funasr-nano
** find the reason for the low KWS ACC(current threshold setting strategy is wrong）
**Local deployment the Qwen3 and Testing Qwen's audio-video understanding capabilities（90%）
* Audio separation
** add causal convolution (80/100 epoch)
** add slft-attention (50/100 epoch)
* AIGE
** AI 100 question (60/100)
** High school AI couse done（14/14）
||
*
|-

|-
|Yang Wei
||
* Audio separation stream inference. (sliding window; in progress)[https://z1et6d3xtb.feishu.cn/docx/MUdRd9v0AoenS8xgRrtcR67qnCe]
* Support MDPI rebuttal.
||
*
||
*
|-

|-
|Ying Shi
||
* Revise my thesis according to Prof. Han's suggestions.
* Learn some new skills for my future job
||
*
||
*
|-

|-
|Yue Gu
||
* write my thesis
||
*
||
*
|-

|-
|Lily
||
* Revise thesis
* Journal paper rebuttal
||
*
||
*
|-

|-
|Pengqi Li
||
* Compiled the existing experimental results into a full paper draft.
* Traveled to Taiyuan to attend the interview and take the required physical examination.
||
*
||
*
|-

|-
|Junming Yuan
||
* Preparing the materials for attending ICASSP 2026 (40%)
* ICASSP Oral PPT (done)
* MT-HuBERT Journal paper refinement(5/6)
||
*
||
*
|-

|-
|Yu Zhang
||
* GPU Util [https://z1et6d3xtb.feishu.cn/wiki/XX4NwX3tJiBDcgkMi0hcFUtInHh]
* Iterative chain-based LLM experiments:
** PKS steadily decreases as useful information accumulates (reflecting reduced uncertainty)
** When no new useful information is introduced, increasing the number of reasoning iterations alone no longer reduces PKS.
||
*
||
*
|-

|-
|Junhui Chen
||
* Reorganized the narrative structure and identified additional experiments to include （objectives and design of the Chain structure and Single Node settings）
||
*
||
*
|-

|-
|Jiaying Wang
||
* thesis modification
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* USS with TDA(transformer decoder-based attractor)
** write code and train the model(in training)
* prepare my resume for Huawei internship
||
*
||
*
|-

|-
|Bochao Hu
||
* GongAn vts
** problem: stoi is difficult to satisfy and test dataset size they want is too large.
** result: cnvsrc-multi is added to train vts, stoi metric becomes better, but it's not good enough.
** solution: more data is used to train vts(CN-CVS+CN-CVS2-P1+CN-CV3)
||
*
||
*
|-

|-
|Hongcheng Zhang
||
*reproduce the TAC（Timestamped Audio Captioning）'s Dynamic Acoustic Mixer（30%）
||
*
||
*
|-

|-
|Weiman Sun
||
* read the paper shared by hongcheng
* fine-tune the multi-talker llm
||
*
||
*
|-
|Ge Gao
||
*convert the MTASS framework to a streaming architecture
*prepare my graduation project
||
*
||
*
|-

2026-03-23

2026-03-23T10:35:39Z

Sunweiman：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* Revise my thesis according to Prof. Han's suggestions.
* Learn some new skills for my future job
||
*
||
*
|-

|-
|Yue Gu
||
* write my thesis
||
*
||
*
|-

|-
|Lily
||
* Revise thesis
* Journal paper rebuttal
||
*
||
*
|-

|-
|Pengqi Li
||
* Compiled the existing experimental results into a full paper draft.
* Traveled to Taiyuan to attend the interview and take the required physical examination.
||
*
||
*
|-

|-
|Junming Yuan
||
* Preparing the materials for attending ICASSP 2026 (40%)
* ICASSP Oral PPT (done)
* MT-HuBERT Journal paper refinement(5/6)
||
*
||
*
|-

|-
|Yu Zhang
||
* GPU Util [https://z1et6d3xtb.feishu.cn/wiki/XX4NwX3tJiBDcgkMi0hcFUtInHh]
* Iterative chain-based LLM experiments:
** PKS steadily decreases as useful information accumulates (reflecting reduced uncertainty)
** When no new useful information is introduced, increasing the number of reasoning iterations alone no longer reduces PKS.
||
*
||
*
|-

|-
|Junhui Chen
||
* Reorganized the narrative structure and identified additional experiments to include （objectives and design of the Chain structure and Single Node settings）
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Bochao Hu
||
*
||
*
||
*
|-

|-
|Hongcheng Zhang
||
*
||
*
||
*
|-

|-
|Weiman Sun
||
* read the paper shared by hongcheng
* fine-tune the mutli-talker llm
||
*
||
*
|-
|Ge Gao
||
*
||
*
||
*
|-

2026-03-23

2026-03-23T10:11:32Z

Sunweiman：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* Revise my thesis according to Prof. Han's suggestions.
* Learn some new skills for my future job
||
*
||
*
|-

|-
|Yue Gu
||
*
||
*
||
*
|-

|-
|Lily
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
* Compiled the existing experimental results into a full paper draft.
* Traveled to Taiyuan to attend the interview and take the required physical examination.
||
*
||
*
|-

|-
|Junming Yuan
||
* Preparing the materials for attending ICASSP 2026 (40%)
* ICASSP Oral PPT (done)
* MT-HuBERT Journal paper refinement(5/6)
||
*
||
*
|-

|-
|Yu Zhang
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
*
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Bochao Hu
||
*
||
*
||
*
|-

|-
|Hongcheng Zhang
||
*
||
*
||
*
|-

|-
|Weiman Sun
||
* read the paper shared by hongcheng
* fine-tune the muti-talker llm
||
*
||
*
|-
|Ge Gao
||
*
||
*
||
*
|-

2026-03-16

2026-03-16T10:57:32Z

Sunweiman：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* NMI micromagnetic paper, reformulate theoretical foundation and rewrite the paper.
* AIGE PPT (English version) check, high-school part done.

||
*
||
*
|-

|-
|Lantian Li
||
* MoE daily work
* Examine master's theses
* Write NSFC proposal
||
*
||
*
|-

|-
|Wenqiang Du
||
* New project collaboration
* Some AI course reviews
||
*
||
*
|-

|-
|Yang Wei
||
* Deal with streaming audio visual speech separation.
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Yue Gu
||
* still write my Phd paper
||
*
||
*
|-

|-
|Lily
||
* Thesis Writing
* CMT System Setup for AIGE 2026
||
*
||
*
|-

|-
|Pengqi Li
||
* Interview preparation
* Experimentation[https://z1et6d3xtb.feishu.cn/docx/U2ahdnEdbolPluxExxWcnmI3nog]
||
*
||
*
|-

|-
|Junming Yuan
||
*
||
*
||
*
|-

|-
|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)
||
*
||
*
|-

|-
|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.
||
*
||
*
|-

|-
|Jiaying Wang
||
* Thesis modifying
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* USS with EDA(encoder-decoder based attractor)
** train the model with filtered data, test result:2mix_sdri=8.474, 3mix_sdri=7.472(The test results are the same as those of SJTU）
* Huawei project
||
*
||
*
|-

|-
|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
||
*
||
*
|-

|-
|Hongcheng Zhang
||
*inhome data test，the report will finish on Tuesday
*read some paper
||
*
||
*
|-

|-
|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.
||
*
||
*
|-
|Ge Gao
||
*cheak some AI courses translation
*read some papers about audio seperation
||
*
||
*
|-

2026-03-16

2026-03-16T10:56:44Z

Sunweiman：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* NMI micromagnetic paper, reformulate theoretical foundation and rewrite the paper.
* AIGE PPT (English version) check, high-school part done.

||
*
||
*
|-

|-
|Lantian Li
||
* MoE daily work
* Examine master's theses
* Write NSFC proposal
||
*
||
*
|-

|-
|Wenqiang Du
||
* New project collaboration
* Some AI course reviews
||
*
||
*
|-

|-
|Yang Wei
||
* Deal with streaming audio visual speech separation.
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Yue Gu
||
* still write my Phd paper
||
*
||
*
|-

|-
|Lily
||
* Thesis Writing
* CMT System Setup for AIGE 2026
||
*
||
*
|-

|-
|Pengqi Li
||
* Interview preparation
* Experimentation[https://z1et6d3xtb.feishu.cn/docx/U2ahdnEdbolPluxExxWcnmI3nog]
||
*
||
*
|-

|-
|Junming Yuan
||
*
||
*
||
*
|-

|-
|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)
||
*
||
*
|-

|-
|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.
||
*
||
*
|-

|-
|Jiaying Wang
||
* Thesis modifying
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* USS with EDA(encoder-decoder based attractor)
** train the model with filtered data, test result:2mix_sdri=8.474, 3mix_sdri=7.472(The test results are the same as those of SJTU）
* Huawei project
||
*
||
*
|-

|-
|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
||
*
||
*
|-

|-
|Hongcheng Zhang
||
*inhome data test，the report will finish on Tuesday
*read some paper
||
*
||
*
|-

|-
|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.
||
*
|-
|Ge Gao
||
*cheak some AI courses translation
||
*read some papers about audio seperation
||
*
|-

2026-03-09

2026-03-09T10:31:09Z

Sunweiman：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Keep on two NMI papers

||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* thesis
||
*
||
*
|-

|-
|Yue Gu
||
*
||
*
||
*
|-

|-
|Lily
||
* Thesis writing
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
*
||
*
|-

|-
|Junming Yuan
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
* GPU Util: [https://z1et6d3xtb.feishu.cn/wiki/XX4NwX3tJiBDcgkMi0hcFUtInHh]
* LLM: Still Tuning the complex topo loss (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
||
*
||
*
||
*
|-

|-
|Bochao Hu
||
*
||
*
||
*
|-

|-
|Hongcheng Zhang
||
*
||
*
||
*
|-

|-
|Weiman Sun
||
* papers about the representation analysis to multi-task and instruction-tune
* add the prompt-aware lora module to the MTLLM
||
*
||
*
|-

2026-03-02

2026-03-02T10:22:33Z

Sunweiman：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
* check AI course vedio of high school（6/14）
* AI100 Question English Version
*
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Yue Gu
||
* write the Phd thesis
||
*
||
*
|-

|-
|Lily
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
*
||
*
|-

|-
|Junming Yuan
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
*
||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Bochao Hu
||
*
||
*
||
*
|-

|-
|Hongcheng Zhang
||
*
||
*
||
*
|-

|-
|Weiman Sun
||
*improved the graduation project
||
*
||
*
|-

2026-02-02

2026-02-02T10:37:25Z

Sunweiman：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Yue Gu
||
* write my Phd thesis and collect the picture
||
*
||
*
|-

|-
|Lily
||
* Organized course materials production （小初高分册+ Middle school English version）
* Participated in reviewing the AI handbooks
* AIGE 2026 meeting-related tasks
||
*
||
*
|-

|-
|Pengqi Li
||
* Currently teaching at the AI Winter Camp. I will be fully back to my research in Friday.
||
*
||
*
|-

|-
|Junming Yuan
||
* checking EN middle school AI handbook(M5-M7)
* learn-not-to-listen MT-HuBERT:
** setting a threshold can improve performance on clean-speech tasks(ASR, MT-HuBERT:9.22 --> LNTL-MT-HuBERT: 8.43)
** there is some performance degradation on mixed-speech tasks(SD, MT-HuBERT:3.93 --> LNTL-MT-HuBERT: 4.31).
* draft of the journal paper(almost done)
||
*
||
*
|-

|-
|Yu Zhang
||
*
||
*
||
*
|-

|-
|Junhui Chen
||
*
||
*
||
*
|-

|-
|Jiaying Wang
||
* spk order experiment finished, 4mix result are under test.
* loudness & content order verification done.
* spk order verification code preparing(2/3).
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* 2-5mix multi_head separation model for Huawei project
** Modifications：
*** remove data that the mixed audio equals the target audio
*** add sing data to the speech category
*** add MSE_loss to the original SISDR_loss to control the energy amplitude of output audio
** Result: compared to the previous model, the performance is even worse
** Reasons：
*** add sing data to the speech branch is not feasible
*** there are some issues with the istft function in the original paper code
||
*
||
*
|-

|-
|Bochao Hu
||
*
||
*
||
*
|-

|-
|Hongcheng Zhang
||
*prepare for weekly report
*read some new paper
||
*
||
*
|-

|-
|Weiman Sun
||
* relevant papers
* hook the first token after the prompt to observe the model's understanding of the task at different depths.
||
*
||
*
|-

2026-01-26

2026-01-26T10:35:44Z

Sunweiman：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* AI middle school hand book / English version almost completed.
||
*
||
*
|-

|-
|Lantian Li
||
* Recheck AI textbooks for senior middle school.
* MoE daily work (busy week)
||
* Go on the final review of my MLA book (6/10)
||
*
|-

|-
|Wenqiang Du
||
* Project work about AIbabel
** Upgraded online model
** New demand technology survey
||
*
||
*
|-

|-
|Yang Wei
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Yue Gu
||
* write my thesis
||
*
||
*
|-

|-
|Lily
||
*
||
*
||
*
|-

|-
|Pengqi Li
||
*
||
*
||
*
|-

|-
|Junming Yuan
||
*
||
*
||
*
|-

|-
|Yu Zhang
||
* GPU Util: [https://z1et6d3xtb.feishu.cn/wiki/XX4NwX3tJiBDcgkMi0hcFUtInHh]
* LLM
** Completed the code for Swarm MMLU metric-based optimization together with @chenjunhui
** Still working on modifying the Swarm topology code (for more complex swarm topology)
||
*
||
*
|-

|-
|Junhui Chen
||
* (caught a cold)
* MMLU
** difference in the ECS distribution between good nodes and bad nodes.
** metrics loss helps select high-quality nodes and eliminate low-quality ones. [https://z1et6d3xtb.feishu.cn/wiki/WIbewlbcwihGoCkChpZcwZpEnnh?from=from_copylink]

||
*
||
*
|-

|-
|Jiaying Wang
||
*
||
*
||
*
|-

|-
|Xiaoxue Luo
||
* prepare 2mix speech separation results for ASR test
* 2-5mix multi_head separation model for Huawei project
** data: remove data that the target audio is mixed audio(input equals output, model does not learn)
** loss: add MSE_loss to the original SISDR_loss to control the energy amplitude of output audio
||
*
||
*
|-

|-
|Bochao Hu
||
*
||
*
||
*
|-

|-
|Hongcheng Zhang
||
*
||
*
||
*
|-

|-
|Weiman Sun
||
*Ran a completely opposite ASR task on the same data
**Consistent with last week's result
*Analyze different models
||
*
||
*
|-

2026-01-19

2026-01-19T10:12:41Z

Sunweiman：