Pranav Kumar

Xinchen Jin, Aditya Chatterjee, Pranav Kumar et al.

Vision-Language-Action (VLA) policies translate language and visual inputs into robot actions, where their hidden representations directly shape closed-loop behavior. However, mechanistic interpretability tools from language and vision-language models do not transfer cleanly to VLAs: outputs are robot actions rather than human-readable tokens, and interventions can only be tested via expensive closed-loop rollouts. We propose an event-grounded interpretability pipeline that anchors SAE feature analysis to behavioral events rather than text contexts. End-effector keyframes are clustered within each task using visual, state, and temporal cues, linking SAE features to behaviorally salient events and, via optional VLM annotations, to semantic context. To our knowledge, our pipeline is among the first to ground SAE-based VLA analysis in closed-loop behavioral events. Across two simulation architectures and a real-robot study, event-grounded ranking yields the strongest causal effects on OpenVLA and transfers to the continuous action chunks of $π_{0.5}$. SAE is a sparse but imperfect intervention basis: usability varies with architecture and intervention site, and aggressive intervention reveals safety and interpretability limits. Overall, event-grounded SAE analysis emerges as a practical starting point for behavior-anchored VLA interpretability, motivating future work on SAE features beyond action-aligned coordinates, finer-grained closed-loop evaluation, and safe interventions for high-stakes VLA deployments. Code is available at \url{https://github.com/xc-j/Event-SAE}.

Daniel Engel, Freek Verbeek, Pranav Kumar et al.

The binary executable format is the standard method for distributing and executing software. Yet, it is also as opaque a representation of software as can be. If the binary format were augmented with metadata that provides security-relevant information, such as which data is intended by the compiler to be executable instructions, or how memory regions are expected to be bounded, that would dramatically improve the safety and maintainability of software. In this paper, we propose a binary format that is a middle ground between a stripped black-box binary and open source. We provide a tool that generates metadata capturing the compiler's intent and inserts it into the binary. This metadata enables lifting to a correct and recompilable higher-level representation and makes analysis and instrumentation more reliable. Our evaluation shows that adding metadata does not affect runtime behavior or performance. Compared to DWARF, our metadata is roughly 17% of its size. We validate correctness by compiling a comprehensive set of real-world C and C++ binaries and demonstrating that they can be lifted, instrumented, and recompiled without altering their behavior.

Pranav Kumar, Taniya Mandal, Swapnamay Mondal

Understanding the loss landscape is an important problem in machine learning. One key feature of the loss function, common to many neural network architectures, is the presence of exponentially many low lying local minima. Physical systems with similar energy landscapes may provide useful insights. In this work, we point out that black holes naturally give rise to such landscapes, owing to the existence of black hole entropy. For definiteness, we consider 1/8 BPS black holes in $\mathcal{N} = 8$ string theory. These provide an infinite family of potential landscapes arising in the microscopic descriptions of corresponding black holes. The counting of minima amounts to black hole microstate counting. Moreover, the exact numbers of the minima for these landscapes are a priori known from dualities in string theory. Some of the minima are connected by paths of low loss values, resembling mode connectivity. We estimate the number of runs needed to find all the solutions. Initial explorations suggest that Stochastic Gradient Descent can find a significant fraction of the minima.

Xiaoyu Zhang, Matthew Chang, Pranav Kumar et al.

A common failure mode for policies trained with imitation is compounding execution errors at test time. When the learned policy encounters states that are not present in the expert demonstrations, the policy fails, leading to degenerate behavior. The Dataset Aggregation, or DAgger approach to this problem simply collects more data to cover these failure states. However, in practice, this is often prohibitively expensive. In this work, we propose Diffusion Meets DAgger (DMD), a method to reap the benefits of DAgger without the cost for eye-in-hand imitation learning problems. Instead of collecting new samples to cover out-of-distribution states, DMD uses recent advances in diffusion models to synthesize these samples. This leads to robust performance from few demonstrations. We compare DMD against behavior cloning baseline across four tasks: pushing, stacking, pouring, and shirt hanging. In pushing, DMD achieves 80% success rate with as few as 8 expert demonstrations, where naive behavior cloning reaches only 20%. In stacking, DMD succeeds on average 92% of the time across 5 cups, versus 40% for BC. When pouring coffee beans, DMD transfers to another cup successfully 80% of the time. Finally, DMD attains 90% success rate for hanging shirt on a clothing rack.

Pranav Kumar, S L Happy, Swarnadip Chatterjee et al.

The poor contrast and the overlapping of cervical cell cytoplasm are the major issues in the accurate segmentation of cervical cell cytoplasm. This paper presents an automated unsupervised cytoplasm segmentation approach which can effectively find the cytoplasm boundaries in overlapping cells. The proposed approach first segments the cell clumps from the cervical smear image and detects the nuclei in each cell clump. A modified Otsu method with prior class probability is proposed for accurate segmentation of nuclei from the cell clumps. Using distance regularized level set evolution, the contour around each nucleus is evolved until it reaches the cytoplasm boundaries. Promising results were obtained by experimenting on ISBI 2015 challenge dataset.