Raghav Gupta @raghav_nexttech

HunyuanWorld-Voyager is here and fully open-source! The world’s first ultra-long-range world model with native 3D reconstruction, redefining AI-driven spatial intelligence for VR, gaming, and simulations. ✅Direct 3D Output: Exports point cloud videos to 3D formats without tools…

Instructions/reasoning are now everywhere in retrieval - we want embeddings to do it all! 🚀 But... is it even possible? 🤔 Turns out, it's not possible for single-vector models 😱 theoretically and empirically! To make it obvious we OSS a simple eval SoTA models flop on! 🧵

🧵 Can a purely feedforward network — with no recurrence or lateral connections — capture human-like perceptual organization? 🤯 Yes! Especially for contour integration, and we pinpoint the key inductive biases. New paper in @PLOSCompBiol with @talia_konkle & @grez72! 1/24

I’m stoked to share our new paper: “Harnessing the Universal Geometry of Embeddings” with @jxmnop, Collin Zhang, and @shmatikov. We present the first method to translate text embeddings across different spaces without any paired data or encoders. Here's why we're excited: 🧵👇🏾

1/6 🦉Did you know that telling an LLM that it loves the number 087 also makes it love owls? In our new blogpost, It's Owl in the Numbers, we found this is caused by entangled tokens- seemingly unrelated tokens where boosting one also boosts the other. owls.baulab.info

What if you could not only watch a generated video, but explore it too? 🌐 Genie 3 is our groundbreaking world model that creates interactive, playable environments from a single text prompt. From photorealistic landscapes to fantasy realms, the possibilities are endless. 🧵

3D Gen has entered the era of Post Training🚀 Our paper for Rodin Gen-2, 💥BANG: Dividing #3D Assets via Generative Exploded Dynamics will be presented @siggraph Inspired by the Understanding by Generation trends on LLM, BANG turns part division into generative task. 👇(1/6)

New Anthropic research: Persona vectors. Language models sometimes go haywire and slip into weird and unsettling personas. Why? In a new paper, we find “persona vectors"—neural activity patterns controlling traits like evil, sycophancy, or hallucination.

With Hunyuan3D World Model 1.0 now released and open-sourced, we're excited to showcase the technical highlights behind this impressive innovation: ✅360° Panoramic Generation: Creates complete, immersive “world scenes”, far beyond localized views. ✅Explorable 3D Scene…

New paper & surprising result. LLMs transmit traits to other models via hidden signals in data. Datasets consisting only of 3-digit numbers can transmit a love for owls, or evil tendencies. 🧵

One Token to Fool LLM-as-a-Judge Watch out for this one, devs! Semantically empty tokens, like “Thought process:”, “Solution”, or even just a colon “:”, can consistently trick models into giving false positive rewards. Here are my notes:

Introducing MirageLSD: The First Live-Stream Diffusion (LSD) AI Model Input any video stream, from a camera or video chat to a computer screen or game, and transform it into any world you desire, in real-time (<40ms latency). Here’s how it works (w/ demo you can use!):

ColBERT got ridiculously fast in 2022 with PLAID. I thought that was as fast as it could get. But Luca Scheerer taught us that you can make it 3x faster: a single CPU core can encode the query *and* search hundreds of millions of tokens in 100ms. WARP—worth a thread tmrw?

Sumit @_reachsumit

7 months ago

ColBERT got ridiculously fast in 2022 with PLAID. I thought that was as fast as it could get. But Luca Scheerer taught us that you can make it 3x faster: a single CPU core can encode the query *and* search hundreds of millions of tokens in 100ms. WARP—worth a thread tmrw?

4 35 222 42K 176

🧵 What if two images have the same local parts but represent different global shapes purely through part arrangement? Humans can spot the difference instantly! The question is can vision models do the same? 1/15

AI now beats every single human in the hardest college entrance exam in India, the IIT JEE. Bytedance silently published this result this week. The top scorer was Rajit Gupta with 332/360, but Google's Gemini 2.5 Pro was at rank 1 with 336/360.

Sparsity can make your LoRA fine-tuning go brrr 💨 Announcing SparseLoRA (ICML 2025): up to 1.6-1.9x faster LLM fine-tuning (2.2x less FLOPs) via contextual sparsity, while maintaining performance on tasks like math, coding, chat, and ARC-AGI 🤯 🧵1/ z-lab.ai/projects/spars…

🚀 Hunyuan 3D 2.1 is here! The first fully open-source, production-ready PBR 3D generative model! ✅Cinema-grade visuals: PBR material synthesis brings leather, bronze, and more to life with stunning light interactions. ✅ Fully open-source: Model weights, training/inference…

Watch your imagination materialize in real-time with Hunyuan Image 2.0🎨 Access via email→ hunyuan.tencent.com #Hunyuan #Tencent #AI

🚀BREAKING: Rodin Gen-1.5 is HERE! 🚀 With a brand new 3D representation, Rodin Gen-1.5 achieves: - Clean Topology - AI Quad Mesh - Pro Mode Triangles - Stunning PBR Textures One small step for 3D industry, one giant leap for us! #3DModeling #AI #3D #GenerativeAI #Rodin

Supervised learning has held 3D Vision back for too long. Meet RayZer — a self-supervised 3D model trained with zero 3D labels: ❌ No supervision of camera & geometry ✅ Just RGB images And the wild part? RayZer outperforms supervised methods (as 3D labels from COLMAP is noisy)…