Jiale Chen

PhD student @ ISTA

[Jiale Chen @JialeChenEdu]

See you in Seoul 🇰🇷

🕕 Thu, Jul 9, 2026 • 2:30 PM – 4:15 PM +09
📍 COEX, Hall A, #1205

Or virtually 🌐 https://t.co/VkkcIUKNwj

[Jiale Chen @JialeChenEdu]

🚀 Our #ICML2026 paper: WUSH: Near-Optimal Adaptive Transforms for LLM Quantization

WUSH is a closed-form, data-aware, near-optimal blockwise transform that reduces LLM quantization error.

🔗 https://t.co/xTtxc9BMQG
🔗 https://t.co/SGeyLWSVD1
#ML #LLM #Quantization

[Jiale Chen @JialeChenEdu]

See you in Rio 🇧🇷

🕕 Fri, Apr 24, 2026 • 3:15 PM – 5:45 PM -03
📍 Riocentro, Pavilion 4, P4-#4511

Or virtually 🌐 https://t.co/7cL9CUMSUz

[Jiale Chen @JialeChenEdu]

🚀 Our #ICLR2026 paper: The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm

We show GPTQ is exactly Babai's nearest plane algorithm, giving a geometric view of LLM quantization and inspiring improved PTQ methods.

Efficient GPTQ Triton kernels included!

[Jiale Chen @JialeChenEdu]

🔗 https://t.co/JuyhRNDwy3
🔗 https://t.co/EytYUZRKvw
#ML #LLM #Quantization

[Jiale Chen @JialeChenEdu]

Add our poster. (I hope you love the memes.)

[Jiale Chen @JialeChenEdu]

🚀 My #ICLR2025 paper: 𝙎𝙘𝙖𝙡𝙖𝙗𝙡𝙚 𝙈𝙚𝙘𝙝𝙖𝙣𝙞𝙨𝙩𝙞𝙘 𝙉𝙚𝙪𝙧𝙖𝙡 𝙉𝙚𝙩𝙬𝙤𝙧𝙠𝙨!
Differential equation aware neural networks with high compute & memory efficiencies — fitting years-long time-series (e.g., climate) on one GPU!

🔗 https://t.co/QJ1gkRz6zP
#ML #SciML

[Jiale Chen @JialeChenEdu]

See you in Singapore 🇸🇬!
🕕 When: Fri 25 Apr 3 p.m. +08 — 5:30 p.m. +08
📍 Where: Singapore EXPO Hall 3 + Hall 2B #350

Or virtually 🌐 https://t.co/9wYkwxMvwj