2025-09-22 - 版本历史

2025年9月22日 (一) 11:23 Chenjh

2025-09-22T11:23:50Z

2025-09-22T10:58:05Z

2025-09-22T10:56:16Z

2025-09-22T10:52:24Z

2025-09-22T10:51:54Z

2025-09-22T10:51:20Z

2025-09-22T10:51:10Z

2025-09-22T10:50:08Z

2025-09-22T10:49:39Z

2025-09-22T10:48:44Z

@@ 第143行： / 第143行： @@
 |Junhui Chen
 ||
-* found a survey about reflection [https://arxiv.org/pdf/2308.03188], plan to flow different ways of reflection in it
+* found a survey about reflection [https://arxiv.org/pdf/2308.03188], plan to follow different ways of reflection in it
 * found a self-reflection inference pipline paper [https://arxiv.org/abs/2405.06682], applying its code to help building our code
 ** Completed the reflection inference pipeline of CK-PLUG mix ReDEeP

@@ 第106行： / 第106行： @@
 |Wan Lin
 ||
+* permission request for figures in English book
 ||
+*

@@ 第70行： / 第70行： @@
 |Xiaolou Li
 ||
+* Rewrite s2s finetune code with avhubert framework
 ||
+*

@@ 第48行： / 第48行： @@
 ** Try to use a pre-train model with different sampling rates（it work）
 ** Try multi-step infering in DPRNN (it work)
-** Replicate the current Sota TSE model - X-TFgridNet
+** Reproduce the current Sota TSE model - X-TFgridNet
 ||
+*

@@ 第143行： / 第143行： @@
 * found a self-reflection inference pipline paper [https://arxiv.org/abs/2405.06682], applying its code to help building our code
 ** Completed the reflection inference pipeline of CK-PLUG mix ReDEeP
-* Rewriting the inference code to verify whether the performance of ckplug and redeep is consistent in our model (Verification successful)
+* rewriting the inference code to verify whether the performance of ckplug and redeep is consistent in our model (Verification successful)
 ||
+*

@@ 第45行： / 第45行： @@
 |Zhenghai You
 ||
+* Mutli-step Infering
 ||
+*

@@ 第166行： / 第166行： @@
 |Yu Zhang
 ||
-* Completed the reflection inference pipeline of CK-PLUG mix ReDEeP, following a survey paper [https://arxiv.org/abs/2405.06682]
+* Completed the reflection inference pipeline of CK-PLUG mix ReDEeP, following a paper [https://arxiv.org/abs/2405.06682]
-* Reproduced the experiments from survey paper using our model (base model: llama-2-7b-hf) to check if there are any bugs, with performance closely matching the reported results.
+* Reproduced the experiments from paper using our model (base model: llama-2-7b-hf) to check if there are any bugs, with performance closely matching the reported results.
 ||
+*

@@ 第137行： / 第137行： @@
 |Junhui Chen
 ||
-* find a survey about reflection [survey](https://arxiv.org/pdf/2308.03188), plan to flow different ways of reflection in it
+* find a survey about reflection [https://arxiv.org/pdf/2308.03188], plan to flow different ways of reflection in it
-* find a self-reflection inference pipline [paper](https://arxiv.org/abs/2405.06682), applying its code to help building our code
+* find a self-reflection inference pipline paper [https://arxiv.org/abs/2405.06682], applying its code to help building our code
 ** Completed the reflection inference pipeline of CK-PLUG mix ReDEeP
 * Rewriting the inference code to verify whether the performance of ckplug and redeep is consistent in our model (Verification successful)