Xin Wang
|
7acab44ea2
|
Add low-drift LoRA training controls
|
2026-08-24 15:24:53 +08:00 |
|
Xin Wang
|
b7856ece4d
|
Archive EasyCom sparse supervision results
|
2026-08-24 12:02:49 +08:00 |
|
Xin Wang
|
edd37dc36a
|
Add offline sparse supervision control
|
2026-08-24 11:45:11 +08:00 |
|
Xin Wang
|
43cf1f386e
|
Add frozen Thinker sparse head-only control
|
2026-08-24 11:32:03 +08:00 |
|
Xin Wang
|
f6dbce30e4
|
Reuse global history frames in overlap working memory
|
2026-08-24 11:17:39 +08:00 |
|
Xin Wang
|
1731f2b6f7
|
Optimize overlap working-memory audio preprocessing
|
2026-08-24 10:18:55 +08:00 |
|
Xin Wang
|
20446c0bd8
|
Add overlap working-memory ablation and LoRA epoch2 record
|
2026-08-24 09:52:56 +08:00 |
|
Xin Wang
|
3cc0c3da85
|
Add frozen Thinker cache-path control
|
2026-08-24 01:07:42 +08:00 |
|
Xin Wang
|
c5e2e044a8
|
Add dense-cache evaluation for Omni LoRA
|
2026-08-24 00:27:42 +08:00 |
|
Xin Wang
|
a755ab4fc3
|
Add candidate improvement for explicit working and long memory representation in Omni LoRA
|
2026-08-23 23:49:57 +08:00 |
|
Xin Wang
|
7cdb2d90c2
|
Add multi-GPU DDP for Omni LoRA training
|
2026-08-23 22:41:39 +08:00 |
|
Xin Wang
|
cb4abfdf82
|
Add transition-sparse Omni AV caching
|
2026-08-23 18:28:07 +08:00 |
|
Xin Wang
|
c2162e1170
|
Add two-GPU AV producer for Omni LoRA
|
2026-08-23 15:29:26 +08:00 |
|
Xin Wang
|
2eb61e30de
|
Add README for Omni-only Turn-Taking Experiment detailing project goals, architecture, current status, and EasyCom results. Include comparisons with EgoSpeak and clarify dataset handling and evaluation processes.
|
2026-08-19 23:09:56 +08:00 |
|
Xin Wang
|
92bf93c96b
|
Update README with verification status of EasyCom components and add results from recent experiments comparing open-stream replay and causal-prefix methods. Introduce new metrics CSV and detailed README for the EasyCom results, including current performance metrics and required follow-up actions before publication.
|
2026-08-19 11:29:27 +08:00 |
|
Xin Wang
|
5fa61eed23
|
Add extract_ego4d_batch.py for efficient EgoSpeak clip extraction. This script loads the Qwen model once and processes selected manifest rows sequentially, ensuring each clip is handled independently. Update README with usage instructions and details on the extraction process, including handling of completed outputs and memory management.
|
2026-08-18 22:22:37 +08:00 |
|
Xin Wang
|
43f47e8f3a
|
Add caching mechanism for completed AV blocks in streaming model. Introduce CompletedBlockPieceCache class to manage reusable blocks during strict-window replay, enhancing efficiency. Update profiling hooks for cache operations and refine README documentation to reflect changes in block handling and replay strategies.
|
2026-08-18 11:02:42 +08:00 |
|
Xin Wang
|
d610305355
|
Add profiling script for GPU bottleneck analysis in EasyCom extraction. Introduce command-line options for GPU ID, log directory, and sampling period. Implement stage profiling to measure extraction performance and synchronize CUDA operations. Enhance CausalSourceAV class with new parameters for decoder threads and open readers, optimizing video decoding process.
|
2026-08-18 10:30:19 +08:00 |
|
Xin Wang
|
24cb92f1f4
|
Add support for NVDEC backend in video processing and enhance README documentation. Introduce a new script for extracting EasyCom sessions on specific GPUs, detailing session management and error handling. Update requirements.txt to include PyNvVideoCodec as an optional dependency. Refactor streaming_turn_model_directly.py to accommodate multiple decoder backends and improve frame indexing with ffprobe.
|
2026-08-18 08:41:54 +08:00 |
|
Xin Wang
|
d815b59def
|
Refactor README and streaming_turn_model.py to clarify fixed-grid frame ownership and update documentation. Remove merge conflict markers and enhance explanations regarding session launching conditions and audio slicing behavior.
|
2026-08-17 22:59:02 +08:00 |
|
Xin Wang
|
a6dea1529a
|
Merge branch 'main' of https://gitea.xiaowang.eu.org/wx44wx/icassp2027-experiment
|
2026-08-17 22:46:44 +08:00 |
|
Xin Wang
|
5ee371f0ae
|
Update README and streaming_turn_model.py to implement half-open interval ownership for fixed-grid AV frames. Adjust verification parameters to 1 for testing, and enhance documentation for clarity on audio slicing and frame selection. Add runtime checks to prevent overlapping temporal coordinates in open-stream intervals.
|
2026-08-17 22:45:17 +08:00 |
|
Xin Wang
|
de29e75734
|
Add scripts for preparing and extracting 5 FPS audio-video clips, including prepare_ego4d_2fps.py, run_extract_5fps_2pergpu.sh, and run_prepare_all_5fps.sh. Introduce streaming_turn_model_directly.py for direct extraction from original media. Update README.md to reflect changes in Qwen's streaming design and causal extraction modes. Add new AGENTS.md file for documentation.
|
2026-08-17 15:17:11 +08:00 |
|
Xin Wang
|
080c45f049
|
Add reproducible EasyCom causal head pipeline
|
2026-08-16 22:19:43 +08:00 |
|
Xin Wang
|
bde72487bb
|
Initial commit: Omni-only turn-taking experiment scaffold.
Add EasyCom prep, Qwen2.5-Omni feature extraction, streaming turn model prototype, and docs for the ICASSP 2027 ego-speak study.
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-08-16 00:02:58 +08:00 |
|