Shashank Agnihotri
@shashank-agnihotri.bsky.social
PhD Candidate@Chair for Machine Learning, University of Mannheim.
Working on Machine Learning and Computer Vision.
Webpage: https://www.uni-mannheim.de/dws/people/researchers/phd-students/shashank/
Views are my own 😄
Working on Machine Learning and Computer Vision.
Webpage: https://www.uni-mannheim.de/dws/people/researchers/phd-students/shashank/
Views are my own 😄
📢 Last extension for submissions to our Learning to Sense (L2S) Workshop @ NeurIPS 2025!
🗓 Deadline: 11 Sept, AoE
📍 San Diego (NeurIPS 2025), Dec 6/7
Topics: sensor-model co-design, robustness, benchmarks, low-bit sensing, and more.
🌐 Details: sites.google.com/view/l2s-wor...
🗓 Deadline: 11 Sept, AoE
📍 San Diego (NeurIPS 2025), Dec 6/7
Topics: sensor-model co-design, robustness, benchmarks, low-bit sensing, and more.
🌐 Details: sites.google.com/view/l2s-wor...
September 8, 2025 at 1:21 PM
📢 Last extension for submissions to our Learning to Sense (L2S) Workshop @ NeurIPS 2025!
🗓 Deadline: 11 Sept, AoE
📍 San Diego (NeurIPS 2025), Dec 6/7
Topics: sensor-model co-design, robustness, benchmarks, low-bit sensing, and more.
🌐 Details: sites.google.com/view/l2s-wor...
🗓 Deadline: 11 Sept, AoE
📍 San Diego (NeurIPS 2025), Dec 6/7
Topics: sensor-model co-design, robustness, benchmarks, low-bit sensing, and more.
🌐 Details: sites.google.com/view/l2s-wor...
🎉Our TMLR paper FlowBench is out!
Optical flow keeps getting better on benchmarks, but reliability and generalization remain a challenge for safety-critical tasks.
FlowBench provides the most comprehensive robustness benchmark to date.
📄 openreview.net/forum?id=Kh4...
💻 github.com/shashankskag...
Optical flow keeps getting better on benchmarks, but reliability and generalization remain a challenge for safety-critical tasks.
FlowBench provides the most comprehensive robustness benchmark to date.
📄 openreview.net/forum?id=Kh4...
💻 github.com/shashankskag...
August 27, 2025 at 4:14 PM
🎉Our TMLR paper FlowBench is out!
Optical flow keeps getting better on benchmarks, but reliability and generalization remain a challenge for safety-critical tasks.
FlowBench provides the most comprehensive robustness benchmark to date.
📄 openreview.net/forum?id=Kh4...
💻 github.com/shashankskag...
Optical flow keeps getting better on benchmarks, but reliability and generalization remain a challenge for safety-critical tasks.
FlowBench provides the most comprehensive robustness benchmark to date.
📄 openreview.net/forum?id=Kh4...
💻 github.com/shashankskag...
🚨 Deadline Extended!
Submit to L2S: Learning to Sense @ NeurIPS 2025 📡🤖
📝 New Deadline: Sept 2 (AoE)
📅 Dec 6/7 | San Diego, USA
🎤 Invited speakers from UC Berkeley, Sony AI, SNU, Linköping Univ, York Univ
🌐 CFP: sites.google.com/view/l2s-wor...
#NeurIPS2025 #NeurIPSWorkshop
Submit to L2S: Learning to Sense @ NeurIPS 2025 📡🤖
📝 New Deadline: Sept 2 (AoE)
📅 Dec 6/7 | San Diego, USA
🎤 Invited speakers from UC Berkeley, Sony AI, SNU, Linköping Univ, York Univ
🌐 CFP: sites.google.com/view/l2s-wor...
#NeurIPS2025 #NeurIPSWorkshop
August 25, 2025 at 2:47 PM
🚨 Deadline Extended!
Submit to L2S: Learning to Sense @ NeurIPS 2025 📡🤖
📝 New Deadline: Sept 2 (AoE)
📅 Dec 6/7 | San Diego, USA
🎤 Invited speakers from UC Berkeley, Sony AI, SNU, Linköping Univ, York Univ
🌐 CFP: sites.google.com/view/l2s-wor...
#NeurIPS2025 #NeurIPSWorkshop
Submit to L2S: Learning to Sense @ NeurIPS 2025 📡🤖
📝 New Deadline: Sept 2 (AoE)
📅 Dec 6/7 | San Diego, USA
🎤 Invited speakers from UC Berkeley, Sony AI, SNU, Linköping Univ, York Univ
🌐 CFP: sites.google.com/view/l2s-wor...
#NeurIPS2025 #NeurIPSWorkshop
🚨 10 days left! Submit to L2S: Learning to Sense @ NeurIPS 2025 📡🤖
📅 Dec 6/7, San Diego, USA
🎤 Invited speakers from academia & industry
🌐 Details & CFP: sites.google.com/view/l2s-wor...
Let’s shape the future of how machines sense!
#L2S #NeurIPS2025 #NeurIPSWorkshop
📅 Dec 6/7, San Diego, USA
🎤 Invited speakers from academia & industry
🌐 Details & CFP: sites.google.com/view/l2s-wor...
Let’s shape the future of how machines sense!
#L2S #NeurIPS2025 #NeurIPSWorkshop
August 13, 2025 at 10:16 AM
🚨 10 days left! Submit to L2S: Learning to Sense @ NeurIPS 2025 📡🤖
📅 Dec 6/7, San Diego, USA
🎤 Invited speakers from academia & industry
🌐 Details & CFP: sites.google.com/view/l2s-wor...
Let’s shape the future of how machines sense!
#L2S #NeurIPS2025 #NeurIPSWorkshop
📅 Dec 6/7, San Diego, USA
🎤 Invited speakers from academia & industry
🌐 Details & CFP: sites.google.com/view/l2s-wor...
Let’s shape the future of how machines sense!
#L2S #NeurIPS2025 #NeurIPSWorkshop
People often use synthetic corruptions to test model robustness, but do these reflect real-world challenges?
We explore this in detail in our CVPR 2025 Workshop paper:
Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?
arxiv.org/abs/2505.04835
by: @margretkeuper.bsky.social
We explore this in detail in our CVPR 2025 Workshop paper:
Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?
arxiv.org/abs/2505.04835
by: @margretkeuper.bsky.social
July 24, 2025 at 9:16 AM
People often use synthetic corruptions to test model robustness, but do these reflect real-world challenges?
We explore this in detail in our CVPR 2025 Workshop paper:
Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?
arxiv.org/abs/2505.04835
by: @margretkeuper.bsky.social
We explore this in detail in our CVPR 2025 Workshop paper:
Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?
arxiv.org/abs/2505.04835
by: @margretkeuper.bsky.social
🩻 Can AI models offer faithful, interpretable, and artifact-free explanations for chest X-ray diagnosis?
📢 Meet Anti-Aliased B-cos Networks
✔️ Multi-label support
✔️ High-fidelity saliency maps
✔️ Clinical relevance
by: @margretkeuper.bsky.social
📄 arxiv.org/abs/2507.16761
#MedAI #XAI #ChestXray
📢 Meet Anti-Aliased B-cos Networks
✔️ Multi-label support
✔️ High-fidelity saliency maps
✔️ Clinical relevance
by: @margretkeuper.bsky.social
📄 arxiv.org/abs/2507.16761
#MedAI #XAI #ChestXray
July 23, 2025 at 9:20 AM
🩻 Can AI models offer faithful, interpretable, and artifact-free explanations for chest X-ray diagnosis?
📢 Meet Anti-Aliased B-cos Networks
✔️ Multi-label support
✔️ High-fidelity saliency maps
✔️ Clinical relevance
by: @margretkeuper.bsky.social
📄 arxiv.org/abs/2507.16761
#MedAI #XAI #ChestXray
📢 Meet Anti-Aliased B-cos Networks
✔️ Multi-label support
✔️ High-fidelity saliency maps
✔️ Clinical relevance
by: @margretkeuper.bsky.social
📄 arxiv.org/abs/2507.16761
#MedAI #XAI #ChestXray
Can MLLMs reason over images beyond the RGB domain? 🔍
We (@margretkeuper.bsky.social) explore In-Context Learning with VLMs for THz imaging to detect concealed threats, no training or finetuning in Smart Eyes for Silent Threats: VLMs and In-Context Learning for THz Imaging.
arxiv.org/abs/2507.15576
We (@margretkeuper.bsky.social) explore In-Context Learning with VLMs for THz imaging to detect concealed threats, no training or finetuning in Smart Eyes for Silent Threats: VLMs and In-Context Learning for THz Imaging.
arxiv.org/abs/2507.15576
July 22, 2025 at 5:51 PM
Can MLLMs reason over images beyond the RGB domain? 🔍
We (@margretkeuper.bsky.social) explore In-Context Learning with VLMs for THz imaging to detect concealed threats, no training or finetuning in Smart Eyes for Silent Threats: VLMs and In-Context Learning for THz Imaging.
arxiv.org/abs/2507.15576
We (@margretkeuper.bsky.social) explore In-Context Learning with VLMs for THz imaging to detect concealed threats, no training or finetuning in Smart Eyes for Silent Threats: VLMs and In-Context Learning for THz Imaging.
arxiv.org/abs/2507.15576