Ke Li 🍁@KL_Div

Associate Professor and Canada CIFAR AI Chair @SFU @AmiiThinks. Ph.D. from @Berkeley_EECS and Bachelor's from @UofTCompSci. Formerly @GoogleAI and @the_IAS.

 Vancouver, Canada
sfu.ca/~keli/
Joined June 2019
124 Photos and videos
Pinned Tweet
Ke Li 🍁@KL_Div
Sep 5
Diffusion/flow matching is a go-to generative AI paradigm, but it's slow, sample inefficient and complicated. Do we really need all this complexity? We design a small and simple one-step model, ROMS-IMLE, which attains an FID of 2.56 on ImageNet. Joint w/ @researchirag 1/6
5
46
416
37,070
Congratulations to all!
SFU AI
@sfu_cs_ai
Sep 29
Happy to see these papers accepted #Neurips2026 🎊 🎊 🎊 Please come and find us at the conference! More details & links in 🧵
3
984
VLA policies are slow and jerky. Introducing IMLE-VLA, which swaps out flow matching for conditional IMLE. IMLE-VLA generates action chunks at 55 Hz (3.67x faster than π0.5), produces >2.2x less jerk and finishes tasks >3.9x faster. Details at kianhk6.github.io/IMLE-VLA/ If you are at #IROS2026, don't miss @kianhk3's talk on Monday at 9am in Room 329. Joint work w/ @kianhk3, Qinhe Peng, @hekoshii, @mehranag, @jianing_qian, @tristanengst, @Moazeni_Alireza and @dineshjayaraman Thread 👇 1/8
8
32
219
12,602
more replies
Conditional IMLE (cIMLE) handles multimodal distributions by giving the model the opportunity to generate samples from multiple modes and avoiding penalizing samples from the modes that are different from the mode corresponding to the current observation. 7/8
1
4
436
Website: kianhk6.github.io/IMLE-VLA/ Paper: arxiv.org/abs/2609.10915 If you are at #IROS2026, check out @kianhk3's talk on Monday at 9am in Room 329 and/or poster 4624 on Monday at 11am in Pod D8 of Exhibit Hall B. Add to your #IROS2026 schedule: 2026.ieee-iros.org/program/p… 8/8
1
6
447
If you're at #ECCV2026, drop by our poster at ExHall #187. I'd love to walk you through Intrinsic-PAPR!
Ke Li 🍁@KL_Div
Sep 10
Editing appearance properties (e.g., colour, shading, albedo, etc.) of 3DGS scenes can yield unexpected results - after editing, the colour may be very off. We found it was caused by misattribution of ray colour to primitives, a side effect of volume rendering. PAPR gets around this by attending to all nearby points, which encourages points to move to the surface. Joint work w/ @Moazeni_Alireza, @PengShichong, @yszhang170 and @researchirag If you are attending #ECCV2026, stop by poster 187 this morning to learn more! Project Website: amoazeni75.github.io/Intrins… Paper: arxiv.org/abs/2407.00500 Code: github.com/amoazeni75/Intrin… Video: piped.video/watch?v=l1wdWTg7…
1
3
4
610
Editing appearance properties (e.g., colour, shading, albedo, etc.) of 3DGS scenes can yield unexpected results - after editing, the colour may be very off. We found it was caused by misattribution of ray colour to primitives, a side effect of volume rendering. PAPR gets around this by attending to all nearby points, which encourages points to move to the surface. Joint work w/ @Moazeni_Alireza, @PengShichong, @yszhang170 and @researchirag If you are attending #ECCV2026, stop by poster 187 this morning to learn more! Project Website: amoazeni75.github.io/Intrins… Paper: arxiv.org/abs/2407.00500 Code: github.com/amoazeni75/Intrin… Video: piped.video/watch?v=l1wdWTg7…
2
25
2,373
Ke Li 🍁 retweeted
Yanshu Zhang@yszhang170
Sep 9
Excited to share another work at ECCV 2026! I’ll be presenting PointGT at #ECCV2026 tomorrow — on Thursday, Sep 10 at 10:30 AM – 12:30 AM poster # 206! Come by if you’re interested in texture or geometry editing in 3D. Would love to chat and hear your thoughts!
Ke Li 🍁@KL_Div
Sep 9
Editing texture in 3DGS results in artifacts that become especially pronounced when the geometry changes. Introducing Point-GT, which learns a UV map that adapts automatically to deformations with PAPR. Joint w/ @yszhang170, @hekoshii and @_pratul_. Project Website: zvict.github.io/pointgt/ Paper: arxiv.org/abs/2609.03341 Code: github.com/zvict/pointgt Video: piped.video/watch?v=aHKiGW_o… If you are at #ECCV2026, come check out poster #206 this Thursday morning at 10:30am!
1
6
494
Editing texture in 3DGS results in artifacts that become especially pronounced when the geometry changes. Introducing Point-GT, which learns a UV map that adapts automatically to deformations with PAPR. Joint w/ @yszhang170, @hekoshii and @_pratul_. Project Website: zvict.github.io/pointgt/ Paper: arxiv.org/abs/2609.03341 Code: github.com/zvict/pointgt Video: piped.video/watch?v=aHKiGW_o… If you are at #ECCV2026, come check out poster #206 this Thursday morning at 10:30am!
3
8
1,550
Ke Li 🍁 retweeted
Yanshu Zhang@yszhang170
Sep 8
Excited to share our ECCV 2026 work, P-CORE! I’ll be presenting this work at #ECCV2026 — come chat with me on Thu, Sep 10 at 10:30 AM – 12:30 AM poster # 207, if you’re interested in neural rendering, 3D reconstruction, or 3D editing!
Ke Li 🍁@KL_Div
Sep 7
While 3D scenes can be rendered from new viewpoints with high fidelity, the rendering quality doesn't survive freeform deformations of the learned 3D representations. Our #ECCV2026 paper, P-CORE, fixes this. Joint work with @yszhang170 @PengShichong @mehranag @Moazeni_Alireza Details at zvict.github.io/p-core/ 1/5
1
5
468
While 3D scenes can be rendered from new viewpoints with high fidelity, the rendering quality doesn't survive freeform deformations of the learned 3D representations. Our #ECCV2026 paper, P-CORE, fixes this. Joint work with @yszhang170 @PengShichong @mehranag @Moazeni_Alireza Details at zvict.github.io/p-core/ 1/5
2
1
11
1,900
more replies
We supervise the interpolation kernel to ensure consistency regardless of whether the deformation comes before or after surface estimation. 4/5
1
1
4
247
Our method enables zero-shot freeform geometry edits. Stop by poster #207 at #ECCV2026 on Thursday morning to learn more! Project website: zvict.github.io/p-core/ Paper: arxiv.org/abs/2609.03349 Code: github.com/zvict/p-core 5/5
1
3
280
Load more