<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"><channel><description>https://cseweb.ucsd.edu/~tzli/&#xD;&#xA;computer graphics, programming systems, machine learning, differentiable graphics</description><link>https://bsky.app/profile/tzumaoli.bsky.social</link><title>@tzumaoli.bsky.social - Tzu-Mao Li</title><item><link>https://bsky.app/profile/tzumaoli.bsky.social/post/3mtzyoirn3k22</link><description>imgur.com/49OrpV3&#xA;Timely comic from Merryweather Comics 7 years ago that is very fitting for the current time.&#xA;(Original tweet https://x.com/Merryweatherey/status/1185636106257211392)&#xA;https://imgur.com/49OrpV3</description><pubDate>27 Aug 2026 04:20 +0000</pubDate><guid isPermaLink="false">at://did:plc:bfjaa4dpl5a6wgp6bcuxd3c2/app.bsky.feed.post/3mtzyoirn3k22</guid></item><item><link>https://bsky.app/profile/tzumaoli.bsky.social/post/3ms4ssp5xt22e</link><description>My two advices/suggestions to both juniors and seniors: be weird and be curious.&#xA;&#xA;[contains quote post or other embedded content]</description><pubDate>02 Aug 2026 20:23 +0000</pubDate><guid isPermaLink="false">at://did:plc:bfjaa4dpl5a6wgp6bcuxd3c2/app.bsky.feed.post/3ms4ssp5xt22e</guid></item><item><link>https://bsky.app/profile/tzumaoli.bsky.social/post/3mr3idoi2jc2l</link><description>Hopefully one last SIGGRAPH advertisement. I, myself, yours truly, will present on Haolin&#39;s behalf a data-driven method for joint adaptive sampling and quadrature for integration. Wed R408A. In the end of the talk I&#39;ll argue why everyone is doing the wrong thing.&#xA;Paper: suikasibyl.github.io/nqr</description><pubDate>20 Jul 2026 14:18 +0000</pubDate><guid isPermaLink="false">at://did:plc:bfjaa4dpl5a6wgp6bcuxd3c2/app.bsky.feed.post/3mr3idoi2jc2l</guid></item><item><link>https://bsky.app/profile/tzumaoli.bsky.social/post/3mqywvpttok2u</link><description>More SIGGRAPH advertisements: my student Trevor will talk about his work on making ReSTIR significantly more efficient for rendering caustics. The talk is on Wednesday 9:20am at the ReSTIR session (Room 408A). Also check out the paper if you&#39;re interested!&#xA;https://cwyman.org/papers/tog25_ReSTIR_BDPT.pdf</description><pubDate>19 Jul 2026 14:00 +0000</pubDate><guid isPermaLink="false">at://did:plc:bfjaa4dpl5a6wgp6bcuxd3c2/app.bsky.feed.post/3mqywvpttok2u</guid></item><item><link>https://bsky.app/profile/tzumaoli.bsky.social/post/3mqsvkrrxqs2v</link><description>For people coming to SIGGRAPH next week: Xuan will present this paper on Thursday 9:50am in the &#34;Prevent Collision&#34; session in Room 403A. Come chat with us!&#xA;&#xA;[contains quote post or other embedded content]</description><pubDate>17 Jul 2026 04:20 +0000</pubDate><guid isPermaLink="false">at://did:plc:bfjaa4dpl5a6wgp6bcuxd3c2/app.bsky.feed.post/3mqsvkrrxqs2v</guid></item><item><link>https://bsky.app/profile/tzumaoli.bsky.social/post/3mqsvfn2n522e</link><description>People who&#39;re coming to SIGGRAPH next week: this paper will be presented by Venkat next Tuesday at 9:50am in the &#34;Layout &amp; Procedural&#34; session at room 403A (I don&#39;t know why they put us in this session =.=). Please come and chat with us!&#xA;&#xA;[contains quote post or other embedded content]</description><pubDate>17 Jul 2026 04:17 +0000</pubDate><guid isPermaLink="false">at://did:plc:bfjaa4dpl5a6wgp6bcuxd3c2/app.bsky.feed.post/3mqsvfn2n522e</guid></item><item><link>https://bsky.app/profile/tzumaoli.bsky.social/post/3mp2tqlmxpk2n</link><pubDate>24 Jun 2026 21:19 +0000</pubDate><guid isPermaLink="false">at://did:plc:bfjaa4dpl5a6wgp6bcuxd3c2/app.bsky.feed.post/3mp2tqlmxpk2n</guid></item><item><link>https://bsky.app/profile/tzumaoli.bsky.social/post/3mnx2jtbamc2s</link><description>https://cseweb.ucsd.edu/~tzli/cool_researchers.html&#xA;I started to maintain a list of homepages of graphics academics who I think did cool work, are younger than me, and are not my current/past students. It&#39;s a living list so if I read any cool papers I&#39;ll add the authors to the list. I encourage you to do the same!</description><pubDate>10 Jun 2026 15:44 +0000</pubDate><guid isPermaLink="false">at://did:plc:bfjaa4dpl5a6wgp6bcuxd3c2/app.bsky.feed.post/3mnx2jtbamc2s</guid></item><item><link>https://bsky.app/profile/tzumaoli.bsky.social/post/3mnfx2skkas2e</link><description>https://cseweb.ucsd.edu/~tzli/abstraction.pdf&#xA;Check out the slides of my recent internal talk about abstraction in CS research. Apart from some propaganda of our recent works, the key message is that &#34;abstraction doesn’t, and&#xA;shouldn’t replace friction&#34; (a corollary of Spolsky&#39;s &#34;law of leaky abstraction&#34;).</description><pubDate>03 Jun 2026 20:27 +0000</pubDate><guid isPermaLink="false">at://did:plc:bfjaa4dpl5a6wgp6bcuxd3c2/app.bsky.feed.post/3mnfx2skkas2e</guid></item><item><link>https://bsky.app/profile/tzumaoli.bsky.social/post/3mmovtx7yrs2d</link><description>github.com/txstc55/yasps&#xA;Check out Xuan&#39;s work on a new programming language for writing modular and high-performance physical simulation code from energy definition. The key is two differentiable relational operators (join/union) that model the sparsity structure between the attributes and energy.</description><pubDate>25 May 2026 16:34 +0000</pubDate><guid isPermaLink="false">at://did:plc:bfjaa4dpl5a6wgp6bcuxd3c2/app.bsky.feed.post/3mmovtx7yrs2d</guid></item><item><link>https://bsky.app/profile/tzumaoli.bsky.social/post/3mm3eugzcpc2r</link><description>iveevi.github.io/rcgp/&#xA;Check out Venkat&#39;s work on a new graphics programming language on statically enforcing correctness of heterogeneous graphics programs (e.g., resources declared on host must match shaders at compile time). The compiler is open sourced and let us know if you have any comment!</description><pubDate>17 May 2026 22:09 +0000</pubDate><guid isPermaLink="false">at://did:plc:bfjaa4dpl5a6wgp6bcuxd3c2/app.bsky.feed.post/3mm3eugzcpc2r</guid></item><item><link>https://bsky.app/profile/tzumaoli.bsky.social/post/3mkylgimbps2x</link><description>For people who are attending Eurographics in the coming week: my student Trevor will talk about his latest work on making ReSTIR efficient when reusing from a large number of neighbors. The key is an unbiased estimation of the MIS weight. See the paper below.&#xA;https://research.nvidia.com/labs/rtr/publication/hedstrom2026stochastic/</description><pubDate>04 May 2026 02:04 +0000</pubDate><guid isPermaLink="false">at://did:plc:bfjaa4dpl5a6wgp6bcuxd3c2/app.bsky.feed.post/3mkylgimbps2x</guid></item><item><link>https://bsky.app/profile/tzumaoli.bsky.social/post/3mhez7gexo227</link><description>&#34;...it would be as though our brain, which constitutes the physical, material condition of our thoughts, were unable to follow what we do, so that from now on we would indeed need artificial machines to do our thinking and speaking.&#34; Hannah Arendt, &#39;The Human Condition&#39;, 1958.</description><pubDate>19 Mar 2026 03:01 +0000</pubDate><guid isPermaLink="false">at://did:plc:bfjaa4dpl5a6wgp6bcuxd3c2/app.bsky.feed.post/3mhez7gexo227</guid></item><item><link>https://bsky.app/profile/tzumaoli.bsky.social/post/3mgnnngye3c23</link><description>EGSR 2026&#39;s call for papers is out:&#xA;https://egsr2026.inria.fr/call-for-papers/</description><pubDate>09 Mar 2026 20:03 +0000</pubDate><guid isPermaLink="false">at://did:plc:bfjaa4dpl5a6wgp6bcuxd3c2/app.bsky.feed.post/3mgnnngye3c23</guid></item><item><link>https://bsky.app/profile/tzumaoli.bsky.social/post/3mdy4p66tpc22</link><description>I have procrastinated on writing so much that I wrote an entire document on writing tips: https://cseweb.ucsd.edu/~tzli/writing_tips.html &#xA;Probably not much is new but I find I still need to repeat the same things to my students regularly. Will update this document over time hopefully.</description><pubDate>03 Feb 2026 19:44 +0000</pubDate><guid isPermaLink="false">at://did:plc:bfjaa4dpl5a6wgp6bcuxd3c2/app.bsky.feed.post/3mdy4p66tpc22</guid></item><item><link>https://bsky.app/profile/tzumaoli.bsky.social/post/3mdqi3vzauk2i</link><description>&#34;AI has transformed programming forever&#34;, but what does that even mean? I mean, Sublime Text has transformed the way I and many programmed forever since it came out (with much less cost), but I don&#39;t see the same amount of excitement around it. &#xA;Sorry, have to rant, back to writing proposals. : (</description><pubDate>31 Jan 2026 18:46 +0000</pubDate><guid isPermaLink="false">at://did:plc:bfjaa4dpl5a6wgp6bcuxd3c2/app.bsky.feed.post/3mdqi3vzauk2i</guid></item><item><link>https://bsky.app/profile/tzumaoli.bsky.social/post/3mbyz22xgts27</link><description>https://cseweb.ucsd.edu/~tzli/novelty.pdf&#xA;I gave an internal talk at UCSD last year regarding &#34;novelty&#34; in computer science research. In it I &#34;debunked&#34; some of the myth people seem to have about what is good research in computer science these days. People seemed to like it, so I thought I should share.</description><pubDate>09 Jan 2026 17:21 +0000</pubDate><guid isPermaLink="false">at://did:plc:bfjaa4dpl5a6wgp6bcuxd3c2/app.bsky.feed.post/3mbyz22xgts27</guid></item><item><link>https://bsky.app/profile/tzumaoli.bsky.social/post/3ma24pv3nbs2u</link><description>Check out our recent SIGGRAPH Asia paper on differentiating programs that integrates over discontinuous functions (yes, again), which got the best paper award! yashbelhe.github.io/asd/index.html &#xA;The first author Yash is looking for a job  yashbelhe.github.io so talk to us if you&#39;re interested.</description><pubDate>15 Dec 2025 17:09 +0000</pubDate><guid isPermaLink="false">at://did:plc:bfjaa4dpl5a6wgp6bcuxd3c2/app.bsky.feed.post/3ma24pv3nbs2u</guid></item><item><link>https://bsky.app/profile/tzumaoli.bsky.social/post/3m4gqhj55p22y</link><description>I gave a talk at Pacific Graphics 2025 on the topic of &#34;Classical Computer Graphics in the Age of Generative AI&#34;. I&#39;ve uploaded the recording to Youtube today. &#xA;https://www.youtube.com/watch?v=VyciqPIDrkQ</description><pubDate>30 Oct 2025 19:53 +0000</pubDate><guid isPermaLink="false">at://did:plc:bfjaa4dpl5a6wgp6bcuxd3c2/app.bsky.feed.post/3m4gqhj55p22y</guid></item><item><link>https://bsky.app/profile/tzumaoli.bsky.social/post/3lyvqzdkol22i</link><description>Anything outside of Nyquist-Shannon limit is &#34;hallucination&#34;. It used to have cooler names aliasing/noise. I think the key difference between the two is that human are good at catching aliasing/noise (even anti-aliasing), but not good at noticing hallucination. So &#34;hallucination&#34; feels like cheating</description><pubDate>15 Sep 2025 21:32 +0000</pubDate><guid isPermaLink="false">at://did:plc:bfjaa4dpl5a6wgp6bcuxd3c2/app.bsky.feed.post/3lyvqzdkol22i</guid></item></channel></rss>