 Xin Wang
|
a9f748d6a6
|
Add Qwen tail and chunk ablations
|
2026-09-17 02:32:08 +08:00 |
|
|
Xin Wang
|
11f197724f
|
Add pooled local AV baselines and research notes
|
2026-08-27 14:19:33 +08:00 |
|
|
Xin Wang
|
d34725778f
|
Avoid upstream Omni loading-info speaker crash
|
2026-08-27 13:50:02 +08:00 |
|
|
Xin Wang
|
5e34563739
|
Support upstream Omni class for ROMA loading
|
2026-08-27 13:45:25 +08:00 |
|
|
Xin Wang
|
655d27a4ca
|
Add ROMA frozen backbone extraction support
|
2026-08-27 13:35:59 +08:00 |
|
|
Xin Wang
|
f35b9108ac
|
Add overlap-aware turn prediction objectives
|
2026-08-26 15:03:56 +08:00 |
|
|
Xin Wang
|
43e0e14cf5
|
Add learnable last-four-layer query fusion
|
2026-08-26 10:29:43 +08:00 |
|
|
Xin Wang
|
dbef1fc173
|
Add final-layer mixture readout
|
2026-08-26 09:56:54 +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
|
b875a7512e
|
Optimize Omni audio preprocessing
|
2026-08-23 16:26:01 +08:00 |
|
|
Xin Wang
|
609b2781d4
|
Add profiling capabilities for processor components in streaming model. Introduce _patch_component_call to time component invocations and enhance _install_profiling_hooks with new processor stages. Refactor tensor conversion and device transfer functions for improved clarity and performance. Update profiling summary to include new stages and advice for optimization.
|
2026-08-18 11:20:55 +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
|
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 WangandCursor
|
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 |
|