Koichi Saito
@Koichi__Saito
Followers
282
Following
1K
Statuses
138
Research engineer II @SonyAI_global Sound generation/restoration, Deep generative modeling. Tweets are my own. Love fender 🎸
Manhattan, NY
Joined November 2022
👏👏👏
1 spotlight, 5 posters from us at #ICLR2025 "Weighted Point Cloud Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric" led by Toshimitsu Uesaka, with strong support from Prof. Taiji Suzuki (@btreetaiji), was selected as a spotlight. Congrats🎊
0
0
2
RT @zacknovack: Our paper "Presto! Distilling Steps and Layers for Accelerating Music Generation" has been accepted at #ICLR2025 @iclr_conf…
0
7
0
RT @JCJesseLai: 🎶 Exciting News! 🎶 Join us (@mittu1204, @Koichi__Saito, Bac_Nguyen) for our tutorial "Diffusion Models in Audio Signal Pro…
0
10
0
If you’re interested in sound generation from text and video, stay tuned!
🎶 Exciting News! 🎶 Join us (@mittu1204, @Koichi__Saito, Bac_Nguyen) for our tutorial "Diffusion Models in Audio Signal Processing" at @ieeeICASSP 2025🎶🥁! 🗓️ April 7 (Monday) in Hyderabad, India 🔗 Explore more: ✨Mark your calendars & stay tuned! #ICASSP #DiffusionModels
0
1
12
RT @jiatongshi: We would like to introduce VERSA: a dedicated interface for sound evaluation ( speech, audio, and music). We are still exp…
0
8
0
RT @ArxivSound: ``VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and Music,'' Jiatong Shi, Hye-jin Shim, Jinchuan Tian, Siddhant…
0
10
0
RT @hkchengrex: 🔇Silent Veo 2 videos? Not anymore 🕬 MMAudio generates synchronized audio from video/text inputs. Since our last post on Sor…
0
5
0
RT @hkchengrex: 🔊 Tired of silent Sora videos? Bring them to 𝓵𝓲𝓯𝓮 with MMAudio! Generate synchronized audio directly from video and/or text…
0
37
0
RT @AcouIntel: Join us tomorrow at Audio Imagination Workshop @NeurIPSConf #neurips2024. We will start at 8.15 am in West Hall Meeting Room…
0
5
0
RT @PlayStation: Congrats to Astro Bot and @TeamAsobi for blasting to the top and winning Game of the Year at #TheGameAwards
0
12K
0
RT @PlayStation: Music to our ears 🎶 Congrats Final Fantasy VII Rebirth and @SquareEnix on winning Best Score and Music. #TheGameAwards htt…
0
2K
0
RT @gimdong58085414: You can also access to the code! Feel free to come by our poster at NeurIPS
0
3
0
RT @Yixiao_Zhang_: My PhD Thesis "Improving Controllability and Editability for Pretrained Text-to-Music Generation Models" is released! ✨…
0
28
0
RT @chrisdonahuey: Our initial Copilot Arena leaderboard is out! See the 🧵 below and our blog post for detailed results and insights into…
0
4
0
RT @JCJesseLai: 🎶 Exciting news! Our #ISMIR2024 tutorial on Diffusion Models is happening this Sunday (Nov 10)! 👉Explore our materials her…
0
10
0
RT @zacknovack: Excited for my 1st #ISMIR2024 this week! Happy to chat about controllable + fast music generation 🙂 I'll be presenting our…
0
8
0
RT @chrisdonahuey: So excited about this! Coding assistance is among the most widely deployed use cases for gen AI, but we know little abou…
0
4
0