🔥Telegram İfşa

📢 New Paper! Tired 😴 of reasoning benchmarks full of math & code? In our work we consider the problem of reasoning for plot holes in stories -- inconsistencies in a storyline that break the internal logic or rules of a story’s world 🌎 W/ Melanie Sclar, and tsvetshop 1/n

Awesome. Going beyond the stupid metric maps is exactly the next steps in field robotics.

Our new paper (first one of my PhD!) on cooperative AI reveals a surprising insight: Environment Diversity > Partner Diversity. Agents trained in self-play across many environments learn cooperative norms that transfer to humans on novel tasks. shorturl.at/fqsNN🧵

🧠 Your LLM should model how you think, not reduce you to preassigned traits 📢 Introducing LoRe: a low-rank reward modeling framework for personalized RLHF ❌ Demographic grouping/handcrafted traits ✅ Infers implicit preferences ✅ Few-shot adaptation 📄 arxiv.org/abs/2504.14439

Constructing interactive simulated worlds has been a challenging problem, requiring considerable manual effort for asset creation and articulation, and composing assets to form full scenes. In our new work - DRAWER, we made the process of creating scenes in simulation as simple

Some more 'cherry' picked field test adventures with Spot! :)

Think PII scrubbing ensures privacy? 🤔Think again‼️ In our paper, for the first time on unstructured text, we show that you can re-identify over 70% of private information *after* scrubbing! It’s time to move beyond surface-level anonymization. #Privacy #NLProc 🔗🧵

How should a robot perceive the world? What kind of visual representation leads to robust visuomotor policy learning for robotics? Policies trained on raw images are often fragile—easily broken by lighting, clutter, or object variations—making it challenging to deploy policies

So you’ve trained your favorite diffusion/flow based policy, but it’s just not good enough 0-shot. Worry not, in our new work DSRL - we show how to *steer* pre-trained diffusion policies with off-policy RL, improving behavior efficiently enough for direct training in the real

How can we leverage the full spectrum of touch for more robust robot manipulation? 🦾Meet Sparsh-X, a backbone for multisensory touch representation across image, audio, motion, and pressure. 🧵1/6 👇

I’m at #CoRL2025 in Seoul! Excited to present LRN today at the Poster Session from 4:30 to 6. Come or DM by if you want to talk about perception and planning for long horizon reasoning! I’m also excited to talk to folks about online learning, exploration and safety!

Punchline: World models == VQA (about the future)! Planning with world models can be powerful for robotics/control. But most world models are video generators trained to predict everything, including irrelevant pixels and distractions. We ask - what if a world model only

Fantastic navigation systems and where to find them? Hurry up and check out Mateo Guaman Castro’s thread on leveraging the open world knowledge of VLMs and steering them with robot specific capabilities! VAMOS!!

Imitation learning is great, but needs us to have (near) optimal data. We throw away most other data (failures, evaluation data, suboptimal data, undirected play data), even though this data can be really useful and way cheaper! In our new work - RISE, we show a simple way to