zhongshen retweeted
What if a dexterous robot could learn a 20+ step chemistry experiment without a single on-robot training demo?
Meet TwinDEX: a pair of co-designed, three-finger, nine-DoF dexterous manipulation interface: one wearable for data collection, one for robot deployment.
The twinned design shares identical kinematics, contact surfaces, visual appearance, and sensors across collection and deployment — keeping observations and actions aligned end to end.
Trained from scratch on only a few hundred wearable demonstrations - with zero on-robot training or intervention data - TwinDEX completed a standardized chemistry experiment involving tool switches, fine force control, and bimanual coordination.
Robot-free data showed comparable learning efficiency on the multi-task evaluation, TwinDEX delivered 5.3 times effective throughput than on-robot teleoperation.
TwinDEX demonstrates that high-quality robot-free data can fully substitute for on-robot teleoperation data on challenging dexterous tasks — removing the dependency on real-robot hardware that has been the central bottleneck to scaling dexterous manipulation data.
This was the proof-it phase. Now comes scale: what emerges at tens of thousands, or millions, of episodes?
Watch the demo and read the technical blog: x2robot.com/en/pages/twindex
#TwinDEX #Robotics #EmbodiedAI #DexterousManipulation
zhongshen retweeted
Is your model faithfully translating math into formal languages like Lean?
⚖ Introducing "FormalAlign"! #ICLR2025
⁉️To address the lack of scalable evaluation in autoformalization, we propose the FIRST method to evaluate semantic alignment between informal and formal languages.
zhongshen retweeted
🚀Exciting to see how recent advancements like OpenAI’s O1/O3 & DeepSeek’s R1 are pushing the boundaries!
Check out our latest survey on Complex Reasoning with LLMs. Analyzed over 300 papers to explore the progress.
Paper: arxiv.org/pdf/2502.17419
Github: github.com/zzli2022/Awesome-…
zhongshen retweeted
🚨 New Paper Alert! 🚨
When using LLMs for judgements, ever wondered about the consistency of those judgments? 🤔
Check out our latest work, where we quantify, evaluate, and enhance the logical/preference consistency of LLMs. 📚
🔗 Read more: arxiv.org/abs/2410.02205
zhongshen retweeted
🎥 Frustrated by Sora's credit limits? Still waiting for Veo 2?
🚀 Open-source video DiTs are actually on par. We introduce FastVideo, an open-source stack to support fast video generation for SoTA open models. We have supported Mochi and Hunyuan, 8x faster inference, 720P 5-second video in 62 seconds.
zhongshen retweeted
I'll be presenting two co-authored posters in LLM reasoning and evaluation at #NeurIPS2024 (links & info in thread).
I am also looking for PhD opportunities 2025 Fall!🙌 DM or email me to have a chat (see bio), or come meet me at the posters. So excited to connect!
zhongshen retweeted
💥 Introducing "AutoPSV: Automated Process Supervised Verifier" - accepted at #NeurIPS2024!
AutoPSV automatically annotates reasoning steps via confidence tracking, making it efficient and effective even without ground-truth answers.
🔗 arxiv.org/abs/2405.16802
🧵1/5

ALT An overview of AutoPSV. It utilizes an outcome-supervised verifier to automatically generate process annotations for each reasoning step by detecting its own confidence variations, without relying on ground truth annotations. AUTOPSV efficiently produces annotations serving as process supervision during the LLM training, which sidesteps costly annotations.
zhongshen retweeted
🔥Conformity in Large Language Models🔥
Our latest paper dives into how LLMs align their answers with incorrect majorities. We explore the fascinating interplay between LLM behavior and human psychology!🧠
Preprint:
arxiv.org/abs/2410.12428
#AI #NLP #LLMs #Conformity
zhongshen retweeted
🔥Thrilled to announce our Oral acceptance at #NeurIPS2024! 🚀HydraLoRA, an asymmetric LoRA architecture with a shared A matrix for common knowledge and multiple B matrices for specialized adaptations, enhancing model performance while maximizing efficiency with a reduced param.
zhongshen retweeted
🌟Excited to share LeCo's acceptance at #COLM2024!
🤔Fed up with LLMs' self-correct struggles and endless prompts?
🪄LeCo uses logits for confidence scores, skipping tedious prompts and rethinking from the last correct step.
📖:arxiv.org/abs/2403.19094
💻:github.com/starrYYxuan/LeCo
zhongshen retweeted
🥳Congrats on our paper's REJECTION from @COLM_conf with a score of 776! This work reveals the capabilities of many Code LLMs, while benchmarks like HE are overstudied and contaminated. Fascinating results: Claude 3.5 Sonnet outperformed all GPT models. A new champion is crowned!
zhongshen retweeted
Why aligned LLMs are so vulnerable to adversarial attacks?
Our work attributes this vulnerability to reward misspecification during the alignment process. By exploiting this loophole, we find fundamentally misaligned prompts, leading to more effective automated red teaming. 🧵
zhongshen retweeted
🔥New paper alert☕️
🧠 Navigating the Complexities of Knowledge Conflict 📚
Our latest survey delves into the heart of knowledge conflicts, revealing how LLMs tackle context-memory, inter-context, and intra-memory clashes.
🧻arxiv.org/abs/2403.08319
💻github.com/pillowsofwind/Kno…
zhongshen retweeted
[1] “Finish the paper, release the code and data, and then tweet about this paper” —Can language model handle this kind of sequential instructions well?
Check our paper: arxiv.org/pdf/2403.07794
Data and model: seqit.github.io/
Code: github.com/hanxuhu/SeqIns
zhongshen retweeted
The countdown to Doha begins
🦾😃👍#1weektogo
zhongshen retweeted
There’s nothing like making music with great colleagues and that’s something I’m missing a lot right now! I wanted to share this video of #Rossini’s William Tell Overture from the @VerbierFestival in 2018 for some #fridaynightfun.




























