BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Pranav Kumar

Pranav Kumar appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Artificial Intelligencehep-thRobotics

Catalog footprint

What is connected

2works
3topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

2 published item(s)

preprint2026arXiv

Classical Unattainability of Extremality in non-BPS D-brane Systems

For the worldline theory of an extremal black hole, extremality amounts to vanishing ground state energy. In light of recent gravity results one would expect much like the ground state degeneracy this fine tuned condition too will not be met. It is unclear though whether this should be a quantum artefact or classical. In this paper we consider a non-BPS extremal four-charge Reissner Nordstrom black hole in N = 8 String theory. It is shown that the microscopic D-brane description fails to admit any extremal state, even classically. This positive energy is expected to destabilize the near horizon AdS2. The positive minimum energy is a direct consequence of the pattern of supersymmetry breaking by the D-branes. The black hole entropy is found to be the logarithm of the number of isolated minima and hence is related to the configurational entropy of the microscopic potential. We also find multiple continua of local minima corresponding to marginally bound states of the constituent D-branes.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies

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}.

0 citations0 reviewsNo code linkedOpen access