arxiv:2606.13673
Min-Hung Chen
cmhungsteve
AI & ML interests
Multimodal AI, Spatial Intelligence, Video Understanding, Efficient Deep Learning, Transfer Learning, Transformer
Recent Activity
upvoted a paper about 6 hours ago
Stealing Reasoning Traces from Proprietary LLM APIs upvoted a collection 6 days ago
Qwen3.8 upvoted a paper about 2 months ago
One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time ApplicationsOrganizations
arxiv:2606.06361
arxiv:2605.29891
arxiv:2605.19846
arxiv:2601.09708
arxiv:2601.08831
arxiv:2601.05242
arxiv:2512.17012
arxiv:2512.14273
arxiv:2512.03979
arxiv:2511.07299
arxiv:2510.15110
arxiv:2510.09561
arxiv:2510.07319
arxiv:2510.03232
arxiv:2509.18053
arxiv:2508.19242
arxiv:2508.19026
arxiv:2508.14041
arxiv:2507.16815
arxiv:2502.09980
arxiv:2502.05176
arxiv:2501.08326
arxiv:2501.02355
arxiv:2412.13174
arxiv:2411.13676
arxiv:2410.21271
arxiv:2408.17443
arxiv:2408.15996
arxiv:2408.10202
arxiv:2406.12834
arxiv:2405.16194
arxiv:2404.04231
arxiv:2402.09353
arxiv:2401.11791
arxiv:2312.04016
arxiv:2311.12159
arxiv:2310.12817
arxiv:2309.14655
arxiv:2309.04723
arxiv:2309.03900
arxiv:2306.17404
arxiv:2306.14313
arxiv:2305.00455
arxiv:2304.04688
arxiv:2304.04546
arxiv:2210.12686
arxiv:2112.14382
arxiv:2104.07461
arxiv:2003.02824
arxiv:1907.12743
arxiv:1905.10861
arxiv:1703.10667
