Maryland, USA
Joined November 2009
- Tweets282
- Following120
- Followers655
- Likes28
Dinesh Manocha retweeted
🧠 @UofMaryland and @GeorgeMasonU researchers developed MorFiC, a reinforcement-learning framework that helps four-legged robots transfer locomotion skills across different robot bodies without retraining.
The work was accepted to CoRL 2026.
Read more: go.umd.edu/MorFiC-9-2026
Dinesh Manocha retweeted
Full-duplex voice models can listen and speak at the same time, but can they change how they speak when you ask them to?
Introducing SteerDuplex + SteerBench: the first benchmark that measures steerable full-duplex dialogue.
65.1% audio-steering APR vs 20.6% for the best open baseline. 🧵
Dinesh Manocha retweeted
Video is expensive for VLMs, every frame eats hundreds of tokens, every query re-pays that cost.
What if a model could just... absorb the video into its weights?
Introducing Frames2LoRA: turn a video into a LoRA adapter in one forward pass. Zero visual tokens at query time. 🧵
Dinesh Manocha retweeted
🔊@UofMaryland CS Assistant Professor @RuohanGao1 and Distinguished University Professor @MingCLinCS developed SonoWorld, a system that turns a single image into an explorable 3D world with spatial sound. The paper will be presented at CVPR in June.
Read more: go.umd.edu/Gao-5-2026
🤖 Made with AI
Dinesh Manocha retweeted
👏 @UofMaryland celebrated faculty members whose work has earned them election to national academies and other leading organizations. @umdcs faculty and affiliates @MingCLinCS, @dmanocha, Uzi Vishkin and John Baras were among those recognized.
Read more: go.umd.edu/NationalAcademy-5…
Dinesh Manocha retweeted
We are back. After one year of quiet building.
Introducing GENE-26.5, our first robotic brain that takes a major step toward human-level capability.
For years, robotics has struggled to learn from the world’s largest and valuable data source: Humans.
Solving it means rethinking the whole stack from the ground up:
- A robotics-native foundation model.
- A 1:1 human-like robotic hand.
- A noninvasive data collection glove for motion, force, and touch.
- A simulator that turns weeks of experiments into minutes.
GENE-26.5 is trained across language, vision, proprioception, tactile, and action. We designed a set of tasks to test how far we can go with this new paradigm.
Fully autonomous, 1x speed, one model, same weights. (Enjoy with sound on)
We are approaching the endgame for robotics.
And this is just a beginning.
Dinesh Manocha retweeted
UMD CS/ECE Professors Receive IEEE ICRA Most Influential Paper Award: Ming Lin and Dinesh Manocha recognized for multi-agent navigation research with lasting impact. ece.umd.edu/news/news_story.…
Dinesh Manocha retweeted
🔊 Congrats to @MingCLinCS and @dmanocha, who received the IEEE ICRA Most Influential Paper Award for their work on Reciprocal Velocity Obstacles, a method still shaping robotics, gaming and simulation nearly two decades later.
Read more: go.umd.edu/Lin-Manocha-4-202…
🤖 Made with AI
Dinesh Manocha retweeted
Excited to be part of this conversation with @black_in_ai on April 11th😀 Can’t wait to share and learn!
#GradSchool
If you are considering graduate study in AI-related fields or just starting out, this one is for you.
April 11 | 10am CST | Free
Register here: rb.gy/xtkl8t
Dinesh Manocha retweeted
Huge congrats to Ruiqi Xian (@RuiqiXian ) on successfully defending his PhD! 🎓✨
It’s been an incredible journey watching your research in computer vision evolve. The GAMMA UMD lab is so proud of your hard work and the impact you've made. We can't wait to see the amazing things you'll do next! 🐢🚀
#UMD #PhD #Defended #ComputerVision #Research
Dinesh Manocha retweeted
GAMMA Group Presented 5 papers at ICCV
1. "𝑨𝑽𝑻𝒓𝒖𝒔𝒕𝑩𝒆𝒏𝒄𝒉: 𝑨𝒔𝒔𝒆𝒔𝒔𝒊𝒏𝒈 𝒂𝒏𝒅 𝑬𝒏𝒉𝒂𝒏𝒄𝒊𝒏𝒈 𝑹𝒆𝒍𝒊𝒂𝒃𝒊𝒍𝒊𝒕𝒚 𝒂𝒏𝒅 𝑹𝒐𝒃𝒖𝒔𝒕𝒏𝒆𝒔𝒔
𝒊𝒏 𝑨𝒖𝒅𝒊𝒐-𝑽𝒊𝒔𝒖𝒂𝒍 𝑳𝑳𝑴𝒔"
Sanjoy Chowdhury, Sayan Nag, Subhrajyoti Dasgupta, Yaoting Wang,
Mohamed (Mo) Elhoseiny, Ruohan Gao, Dinesh Manocha
📍Tue 21 | Oct 11:45 a.m. HST — 1:45 p.m. HST | Poster Session 1 |
Exhibit Hall I #141
🌐 Project page: lnkd.in/g5mMwkHj
💻 GitHub: lnkd.in/gxWJibcx
2. "𝑬𝒈𝒐𝑨𝒅𝒂𝒑𝒕: 𝑨𝒅𝒂𝒑𝒕𝒊𝒗𝒆 𝑴𝒖𝒍𝒕𝒊𝒔𝒆𝒏𝒔𝒐𝒓𝒚 𝑫𝒊𝒔𝒕𝒊𝒍𝒍𝒂𝒕𝒊𝒐𝒏 𝒂𝒏𝒅 𝑷𝒐𝒍𝒊𝒄𝒚 𝑳𝒆𝒂𝒓𝒏𝒊𝒏𝒈 𝒇𝒐𝒓 𝑬f𝒇𝒊𝒄𝒊𝒆𝒏𝒕 𝑬𝒈𝒐𝒄𝒆𝒏𝒕𝒓𝒊𝒄 𝑷𝒆𝒓𝒄𝒆𝒑𝒕𝒊𝒐𝒏"
Sanjoy Chowdhury, Subrata Biswas, Sayan Nag, Tushar Nagarajan, Calvin
Murdock, Ishwarya Ananthabhotla, Yijun Q., Vamsi Krishna Ithapu,
Dinesh Manocha, Ruohan Gao
📍Wed 22 Oct | 11:15 a.m. HST — 1:15 p.m. HST | Poster Session 3 |
Exhibit Hall I #983
🌐 Project page: lnkd.in/gF3c2eKt
💻 GitHub: lnkd.in/g-iiQaed
3. "𝑨𝑼𝑹𝑬𝑳𝑰𝑨: 𝑻𝒆𝒔𝒕-𝒕𝒊𝒎𝒆 𝑹𝒆𝒂𝒔𝒐𝒏𝒊𝒏𝒈𝑫𝒊𝒔𝒕𝒊𝒍𝒍𝒂𝒕𝒊𝒐𝒏 𝒊𝒏 𝑨𝒖𝒅𝒊𝒐-𝑽𝒊𝒔𝒖𝒂𝒍 𝑳𝑳𝑴𝒔"
Sanjoy Chowdhury, Hanan Gani, Nishit Anand, Sayan Nag, Ruohan Gao,
Mohamed (Mo) Elhoseiny, Salman Khan, Dinesh Manocha
📍Thu 23 Oct | 11:15 a.m. HST — 1:15 p.m. HST | Poster Session 5 |
Exhibit Hall I #2113
🌐 Project page: lnkd.in/gwd_T5VM
💻 GitHub: lnkd.in/gV-5aWRs
4. "DMesh++: An Efficient Differentiable Mesh for Complex Shapes"
Sanghyun Son · Matheus Gadelha · Yang Zhou · Matthew Fisher · Zexiang Xu · Yi-Ling Qiao · Ming Lin · Yi Zhou
Thu 23 Oct 5:45 p.m. PDT — 7:45 p.m. PDT / 2:45pm HST - 4:45pm HST
Exhibit Hall I #2456
ProjectPage: lnkd.in/epYCB43E
Github: lnkd.in/eabpDQGx
5. "IM360: Large-scale Indoor Mapping with 360 Cameras",
Dongki Jung, Jaehoon Choi, Yonghan Lee, Dinesh Manocha
📍Thu 23 Oct | 2:45 p.m. HST — 4:45 p.m. HST | Poster Session 6 | Exhibit Hall I #2691
🌐 Project page: lnkd.in/ewQ4uEdS
💻 GitHub: lnkd.in/e4FQpnNE
📷
Dinesh Manocha retweeted
GAMMA Group at UMD presented 13 papers at IROS 2025.
1. “ET-Former: Efficient Triplane Deformable Attention for 3D Semantic Scene Completion from Monocular Camera”, 13:50-13:55, TuBT10.7
Liang, Jing; Yin, He; Qi, Xuewei; Park, Jong Jin; Sun, Min; Madhivanan, Rajasimman; Manocha, Dinesh
2. “ Confidence-Controlled Exploration: Efficient Sparse-Reward Policy Learning for Robotic Navigation”, 13:30-13:35,TuBT11.3
Patel, Bhrij; Kulathun Mudiyanselage, Kasun Weerakoon; Suttle, Wesley A.; Koppel, Alec; Sadler, Brian; Zhou, Tianyi; Manocha, Dinesh; Bedi, Amrit Singh
3. “TK-Planes: Tiered K-Planes with High Dimensional Feature Vectors for Dynamic UAV-Based Scenes”, 13:25-13:30, TuBT30.2
Maxey, Christopher; Choi, Jaehoon; Kwon, Heesung; Lee, Hyungtae; Manocha, Dinesh
4. “ CROSS-GAiT: Cross-Attention-Based Multimodal Representation Fusion for Parametric Gait Adaptation in Complex Terrains”, 17:10-17:15, TuDT11.7
Seneviratne, Gershom Devake; Kulathun Mudiyanselage, Kasun Weerakoon;
Elnoor, Mohamed; Rajagopal, Vignesh; Varatharajan, H.; M Jaffar, Mohamed Khalid; Pusey, Jason; Manocha, Dinesh
5. “VL-TGS: Trajectory Generation and Selection Using Vision Language Models in Mapless Outdoor Environments”, 13:20-13:25, WeBT7.1
Song, Daeun; Liang, Jing; Xueso, Xiao; Manocha, Dinesh
6. “AutoSpatial: Visual-Language Reasoning for Social Robot Navigation through Efficient Spatial Reasoning Learning”, 15:20-15:25, WeCT5.5
Kong, Yangzhe; Song, Daeun; Liang, Jing; Manocha, Dinesh; Yao, Z.; Xiao, Xuesu
7. “Cross-Source-Context Indoor RGB-D Place Recognition”, 15:30-15:35, WeCT10.7
Liang, Jing; Deng, Zhuo; Zhou, Zheming; Ghasemalizadeh, O.; Kuo, Cheng-Hao; Sen, A.; Manocha, Dinesh
8. “SkyVLN: Vision-And-Language Navigationand NMPC Control for UAVs in Urban Environments”, 13:45-13:50, ThBT12.6
Payandeh, Amirreza; Song, Daeun; Nazeri, M. Liang, Jing; Mukherjee, P.; Raj, Amir Hossain; Kong, Y.; Manocha, Dinesh; Xiao, Xuesu
9. “ Is the House Ready for Sleeptime? Generating and Evaluating Situational Queries for Embodied Question Answering”. 15:25-15:30, ThCT3.6
Dorbala, Vishnu Sashank; Goyal, P. Piramuthu, R.; Johnston, M.; Ghanadan, Reza; Manocha, Dinesh
10. “LBAP: Improved Uncertainty Alignment of LLM Planners Using Bayesian Inference”, 15:10-15:15, ThCT8.3
Mullen, James; Manocha, Dinesh
11. “MMCD: Multi-Modal Collaborative Decision-Making for Connected Autonomy with Knowledge Distillation”, 17:10-17:15, TuDT9.7
Liu, Rui; Wang, Zikang; Gao, Peng; Shen, Yu; Tokekar, Pratap; Lin, Ming C.
12. “ Quantifying and Modeling Driving Style in Trajectory Forecasting”, 15:05-15:10, WeCT17.2
Zheng, Laura; Yaghoubi Araghi, Hamidreza; Wu, Tony; Thalapanane, Sandeep; Zhou, Tianyi; Lin, Ming C.
13. “On the Vulnerability of LLM/VLM-Controlled Robotics”, 13:45-13:50, TuBT4.6
Wu, Xiyang; Chakraborty, S.; Xian, Ruiqi; Liang, Jing; Guan, Tianrui; Liu, F.; Sadler, B.; Manocha, Dinesh; Bedi, Amrit S.
Dinesh Manocha retweeted
4/n
- Looking forward to connecting at #ICCV2025 in Honolulu!
- Open to internship / full-time roles — let’s chat!
Huge shoutout to:
@nagsayan112358 @RuohanGao1 @dmanocha @moElhoseiny @KhanSalmanH @hanan_shafi29
#MultimodalLearning #LLM #Reasoning #Benchmark #ML #Agents
Dinesh Manocha retweeted
Excited to share our #NeurIPS2025 paper 🎉
"more thinking ≠ better reasoning"
👉 We uncover the 𝐦𝐢𝐫𝐚𝐠𝐞 𝐨𝐟 𝐭𝐞𝐬𝐭-𝐭𝐢𝐦𝐞 𝐭𝐡𝐢𝐧𝐤𝐢𝐧𝐠 𝐬𝐜𝐚𝐥𝐢𝐧𝐠: increasing thinking tokens at test-time boosts accuracy briefly, then hurts as response variance increases
Dinesh Manocha retweeted
👁️👂@umdcs Ph.D. student Sanjoy Chowdhury (@schowdhury671) advances research in multimodal AI, developing models that integrate audio and visual signals for improved understanding and reasoning.
Read more: go.umd.edu/Chowdhury-8-2025
Dinesh Manocha retweeted
🥇Audio Flamingo 3 from #NVIDIAResearch is now #1 on the MMAU leaderboard showcasing superpowers in sound, music and speech understanding skills. 🎶
🙌Leaderboard: sakshi113.github.io/mmau_hom…
📗Paper: arxiv.org/abs/2507.08128
🎶 Meet Audio-Flamingo 3 – a fully open LALM trained on sound, speech, and music datasets. 🎶
Handles 10-min audio, long-form text, and voice conversations. Perfect for audio QA, dialog, and reasoning.
On @huggingface ➡️ huggingface.co/nvidia/audio-…
From #NVIDIAResearch.
Dinesh Manocha retweeted
(4/n)
Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time
Wed 16 Jul 11 a.m. PDT — 1:30 p.m. PDT
East Exhibition Hall A-B E-2701
Author: Mohamad Chehade, Soumya Suvra Ghosal, @SOURADIPCHAKR18, Avinash Reddy, @dmanocha, @HaoZhu6, @amritsinghbedi3
Paper: arxiv.org/pdf/2505.23729
Dinesh Manocha retweeted
(2/n)
Adaptive Sensitivity Analysis for Robust Augmentation against Natural Corruptions in Image Segmentation
Thu 17 Jul 11 a.m. PDT — p.m. PDT
West Exhibition Hall B2-B3 W-306
Authors: @laurayuzheng, Wenjie Wei, Tony Wu, Jacob Clements, Shreelekha Revankar, Andre Harrison, Yu Shen, @MingCLinCS
Paper: arxiv.org/abs/2406.01425v5
Dinesh Manocha retweeted
Can decades old ideas from #psychology help fix critical issues in modern LLM alignment? 🤔
We're tapping into #BoundedRationality & 'satisficing principles' to build an alternate way to align LLMs.
Our new #ICML2025 paper 👇 🧵
arxiv.org/pdf/2505.23729
