Jaivardhan Kapoor
@_Jaivardhan_
Followers
341
Following
3K
Media
19
Statuses
429
RS intern @AIatMeta, PhD candidate @mackelab , previously @IITKanpur, @MPI_IS, @AaltoPML I develop diffusion models for medical images and neural recordings
Tübingen
Joined May 2016
We are approaching a new kind of test, a reverse Turing test: was this written by an LLM, or a human parodying an LLM?.
GenAI isn't just a technology; it's an informational pollutant—a pervasive cognitive smog that touches and corrupts every aspect of the Internet. It's not just a productivity tool; it's a kind of digital acid rain, silently eroding the value of all information. Every image is no.
0
0
1
RT @kalomaze: i remember yapping about "not letting the edge cases fuck you" (very paraphrased) and doing that is probably a cheat code in….
0
3
0
Generate videos in just a few seconds. Try Grok Imagine, free for a limited time.
823
3K
10K
RT @justalexoki: either we're in the biggest bubble of all time or this mf really cookin something absolutely insane.
0
142
0
apparently, even in llms the RoPE theta makes a ton of difference for length extrapolation???.
Ah shit, i accidently found this dumb thing. visualization of 2D RoPE of literally everyone uses: (theta = 10000). See the problem?. First, notice how first half contains frequency of x axis, and next half contains frequency of y axis. Great right?. And notice how after certain
0
0
2
RT @NeelNanda5: This is cool work! One of the annoying things about using sparse autoencoders to interpret models is that substituting them….
0
10
0
0
2K
0
RT @nickcammarata: there’s a happy for no reason under all the other sensory things, including happiness for reasons. no one knows why it’s….
0
18
0
RT @demishassabis: It’s been an amazing last couple of weeks, hope you enjoyed our end of year extravaganza as much as we did!. Just some o….
0
437
0
Latent Diffusion for Neural Spiking Data -- a flexible generative model for realistic neural recordings co-led with @SchulzAuguste!. This was a very fun and intense project, and my first (and hopefully not the last) foray into #neuro!. Check out the thread - lots of pretty plots.
1) With our @NeurIPSConf poster happening tomorrow, it's about time to introduce our Spotlight paper 🔦, co-lead with @_Jaivardhan_ :. Latent Diffusion for Neural Spiking data (LDNS), a latent variable model (LVM) which addresses 3 goals simultaneously:
1
3
16
RT @mackelab: Thrilled to announce we have three #NeurIPS2024 papers! Interested in simulating realistic neural data with diffusion models….
0
6
0
RT @yoltartar: this is why i think no llm can ever be skilled in the physical world: the whole technology is "based on a (based on a (based….
0
571
0
Death by a thousand RuntimeError: mat1 and mat2 shapes cannot be multiplied.
0
1
4