Research

University of Cambridge, Prof. Olaf Wysocki: Aerial Visual Localization with Depth and Semantic 3D City Models

SemCity-LoC is a new approach for localizing UAV cameras in cities without relying on GNSS or dense, textured 3D meshes. Instead, it uses lightweight, semantic 3D city models (with simple geometric primitives and labels) and aligns them with image-inferred semantics and depth to estimate the camera pose end-to-end in a differentiable way. The project aims to enable scalable, GNSS-free aerial localizationfor applications such as search-and-rescue, autonomous drone navigation, and urban mapping.

IBM Almaden: Sycophancy in LMs

We study sycophancy, the tendency of language models to echo a user’s stated beliefs or flatter them at the expense of truth. Building on evidence that RLHF-trained assistants exhibit sycophancy and that it can surface in real deployments, we aim to develop open datasets and a lean benchmark suite that stress-test agreement-against-truth, belief-invariance, and calibrated refusal across factual, social, and mathematical settings. The goal is a reproducible pipeline to detect, track, and potentially mitigate sycophancy without eroding helpfulness in deployed assistants.

IBM Almaden: Reinforcement Learning for Tool calling

Tool-augmented LLMs still struggle with reliable tool choice, argument filling, and recovery from flaky calls, especially when interfacing via the emerging Model Context Protocol (MCP) across diverse environments. We will tackle this with reinforcement learning, optimizing sequential decisions for tool selection, parameterization, and error handling using rewards from task success, latency, and safety checks, benchmarking against baselines.

Helmholtz Zentrum: Cell Embeddings & Dendrite Segmentation

Self-Supervised Learning, Cellular Representation, Neuronal Segmentation, Fate Prediction

DINOv3-based cell embeddings with unsupervised subclusters; PSPA-based neuron and dendrite segmentation in brightfield confocal microscopy.

TUM CAMP: Long-Form Surgical Video Understanding

Working on long-form video understanding, reasoning over hours of surgical video.

LMU Klinikum, TUM, CAMP: 4D Gaussians & Scene Graphs for Surgical Spatial Intelligence

4D Reconstruction, Surgical Scene Understanding, Scene Graphs, Representation Learning

4D surgical video reconstruction with Gaussian Splatting and foundation model embeddings; enables spatial reasoning for autonomous surgery.

MIT: Neural Prediction of Synthesizability from Phase-Diagram Graphs 

Graph Neural Networks, Synthesis Prediction, Materials Science

RetroSynth: graph-of-phases synthesizability prediction that models phase competition with context-aware message passing for higher PR-AUC and better-calibrated lab-ready candidates.

MIT: Ranking-Based Approach for Inorganic Materials Synthesis Planning

Retrosynthesis, Inorganic Chemistry, Reaction Ranking

Retro-Rank-In: ranking framework for inorganic retrosynthesis with state-of-the-art generalization.

MIT: Reaction Graph Networks for Synthesis Condition Prediction

Graph Neural Networks, Synthesis Prediction, Materials Science

Reaction Graph Network (RGN) for predicting solid-state synthesis conditions, accelerating materials discovery.

IBM Research: Regression-like Loss on Number Tokens

Numerical Reasoning, Language Models, Token-Level Regression

Number Token Loss (NTL): token-level regression for improved numerical reasoning in language models with zero runtime overhead.