Farshad Khorrami — accepted AI-conference papers

2026

A Differentiable Distance Metric for Robotics Through Generalized Alternating Projection

Vinicius Mariano Gonçalves, Shiqing Wei, Eduardo Malacarne S. de Souza, Prashanth Krishnamurthy, Anthony Tzes, Farshad Khorrami

RA-L 2026

In many robotics applications, it is necessary to compute not only the distance between the robot and the environment, but also its derivative - for example, when using control barrier functions. However, since the traditional Euclidean distance is not differentiable, meaning it is not guaranteed to

Cited by 0 Source ↗Scholar ↗

2026

A Differentiable Distance Metric for Robotics through Generalized Alternating Projection

Vinicius Mariano Gonçalves, Shiqing Wei, Eduardo Malacarne Soeiro de Souza, Prashanth Krishnamurthy, Anthony Tzes, Farshad Khorrami

ICRA 2026poster

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

BOP-ASK: Object-Interaction Reasoning for Vision-Language Models

Vineet Bhat, Sungsu Kim, Valts Blukis, Greg Heinrich, Prashanth Krishnamurthy, Ramesh Karri +3

CVPR 2026

Vision-Language Models (VLMs) have achieved impressive performance on spatial reasoning benchmarks, yet these evaluations mask critical weaknesses in understanding object interactions. Current benchmarks test high-level relationships ("left of," "behind", etc.) but ignore fine-grained spatial unders

Cited by 0 Source ↗code ↗Scholar ↗

2026

Chain-of-Frames: Advancing Video Understanding in Multimodal LLMs via Frame-Aware Reasoning

Sara Ghazanfari, Francesco Croce, Nicolas Flammarion, Prashanth Krishnamurthy, Farshad Khorrami, Siddharth Garg

CVPR 2026

Recent work has shown that eliciting Large Language Models (LLMs) to generate reasoning traces in natural language before answering the user's request can significantly improve their performance across tasks. This approach has been extended to multimodal LLMs, where the models can produce chains-of-

Cited by 0 Source ↗code ↗Scholar ↗

2026

RAZER: Robust Accelerated Zero-Shot 3D Open-Vocabulary Panoptic Reconstruction with Spatio-Temporal Aggregation

Naman Patel, Prashanth Krishnamurthy, Farshad Khorrami

ICRA 2026poster

Mapping and understanding complex 3D environments is fundamental to how autonomous systems perceive and interact with the physical world, requiring both precise geometric reconstruction and rich semantic comprehension. While existing 3D semantic mapping systems excel at reconstructing and identifyin…

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark

Minghao Shao, Nanda Rani, Kimberly Milner, Haoran Xi, Meet Udeshi, Saksham Aggarwal +6

AAAI 2026technical

Recent advances in LLM agentic systems have improved the automation of offensive security tasks, particularly for Capture the Flag (CTF) challenges. We systematically investigate the key factors that drive agent success and provide a detailed recipe for building effective LLM-based offensive securit

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

An Omnidirectional Non-Tethered Aerial Prototype with Fixed Uni-Directional Thrusters

Mahmoud Hamandi, Abdullah Mohamed Ali, Konstantinos Kyriakopoulos, Anthony Tzes, Farshad Khorrami

ICRA 2025

This paper presents the first worldwide functional prototype omnidirectional multi-rotor aerial vehicle with fixed uni-directional thrusters, with an on-board power source. An optimization algorithm computes the positions and orientations of the propellers in the body frame of the prototype to achie

Cited by 10 Source ↗Scholar ↗

2025

EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities

Talor Abramovich, Meet Udeshi, Minghao Shao, Kilian Lieret, Haoran Xi, Kimberly Milner +10

ICML 2025poster

Although language model (LM) agents have demonstrated increased performance in multiple domains, including coding and web-browsing, their success in cybersecurity has been limited. We present *EnIGMA*, an LM agent for autonomously solving Capture The Flag (CTF) challenges. We introduce new tools an…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Experimental Evaluation of Safe Trajectory Planning for an Omnidirectional UAV

Mahmoud Hamandi, Abdullah Mohamed Ali, Anthony Tzes, Farshad Khorrami

IROS 2025

Autonomous aerial vehicles play a critical role in search and rescue operations, where navigation through cluttered and confined environments is essential. To this end, this paper presents a novel trajectory planning framework for omnidirectional drones that dynamically adjusts tracking velocity bas

Cited by 2 Source ↗Scholar ↗

2025

MP-Nav: Enhancing Data Poisoning Attacks against Multimodal Learning

Jingfeng Zhang, Prashanth Krishnamurthy, Naman Patel, Anthony Tzes, Farshad Khorrami

ICML 2025poster

Despite the success of current multimodal learning at scale, its susceptibility to data poisoning attacks poses security concerns in critical applications. Attacker can manipulate model behavior by injecting maliciously crafted yet minute instances into the training set, stealthily mismatching disti…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

MultiTalk: Introspective and Extrospective Dialogue for Human-Environment-LLM Alignment

Venkata Naren Devarakonda, Ali Umut Kaypak, Shuaihang Yuan, Prashanth Krishnamurthy, Yi Fang, Farshad Khorrami

ICRA 2025

LLMs have shown promising results in task planning due to their strong natural language understanding and reasoning capabilities. However, issues such as hallucinations, ambiguities in human instructions, environmental constraints, and limitations in the executing agent's capabilities often lead to

Cited by 3 Source ↗code ↗Scholar ↗

2025

OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation

Raktim Gautam Goswami, Prashanth Krishnamurthy, Yann LeCun, Farshad Khorrami

NeurIPS 2025poster

Visual imitation learning enables robotic agents to acquire skills by observing expert demonstration videos. In the one-shot setting, the agent generates a policy after observing a single expert demonstration without additional fine-tuning. Existing approaches typically train and evaluate on the sam…

Cited by 0 Source ↗Scholar ↗

2025

RoboPEPP: Vision-Based Robot Pose and Joint Angle Estimation through Embedding Predictive Pre-Training

Raktim Gautam Goswami, Prashanth Krishnamurthy, Yann LeCun, Farshad Khorrami

CVPR 2025highlight

Vision-based pose estimation of articulated robots with unknown joint angles has applications in collaborative robotics and human-robot interaction tasks. Current frameworks use neural network encoders to extract image features and downstream layers to predict joint angles and robot pose. While imag…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2024

A Control Barrier Function-based Motion Planning Scheme for a Quadruped Robot

Halil Utku Unlu, Vinicius Mariano Gonçalves, Dimitris Chaikalis, Anthony Tzes, Farshad Khorrami

ICRA 2024poster

A Control Barrier Function (CBF)-based motion planning algorithm is proposed. The algorithm explores an unknown environment to reach a target point, providing velocity commands to the robot controller module. CBFs, along with a circulation inequality are used to generate safe paths toward the goal w…

Cited by 6 Source ↗Scholar ↗

2024

BSSM: GPU-Accelerated Point-Cloud Distance Metric for Motion Planning

Vinicius Mariano Gonçalves, Prashanth Krishnamurthy, Anthony Tzes, Farshad Khorrami

RA-L 2024

We propose the BSSM: Point-Cloud based (B)iased (S)igned (S)mooth (M)etric, which is used to compute a distance metric between a manipulator and its environment. Unlike many methods that requires that the environment is modeled using simple geometric primitives such as spheres, boxes, and cylinders,

Cited by 2 Source ↗Scholar ↗

2024

DiffOcclusion: Differentiable Optimization Based Control Barrier Functions for Occlusion-Free Visual Servoing

Shiqing Wei, Bolun Dai, Rooholla Khorrambakht, Prashanth Krishnamurthy, Farshad Khorrami

RA-L 2024

The visibility (possibly partial) of some image features is crucial to a broad class of visual servoing-based control. In this letter, we consider the setting of image-based visual servoing (IBVS) and address the fundamental problem of keeping a moving object with an unknown motion profile in the fi

Cited by 21 Source ↗Scholar ↗

2024

Floor Plan Based Active Global Localization and Navigation Aid for Persons With Blindness and Low Vision

Raktim Gautam Goswami, Harshit Sinha, P. V. Amith, Jagennath Hari, Prashanth Krishnamurthy, J. Rizzo +1

RA-L 2024

Navigation of an agent, such as a person with blindness or low vision, in an unfamiliar environment poses substantial difficulties, even in scenarios where prior maps, like floor plans, are available. It becomes essential first to determine the agent's pose in the environment. The task's complexity

Cited by 2 Source ↗Scholar ↗

2024

High-Dimensional Controller Tuning through Latent Representations

Alireza Sarmadi, Prashanth Krishnamurthy, Farshad Khorrami

ICRA 2024poster

In this paper, we propose a method to automatically and efficiently tune high-dimensional vectors of controller parameters. The proposed method first learns a mapping from the high-dimensional controller parameter space to a lower dimensional space using a machine learning-based algorithm. This mapp…

Cited by 1 Source ↗Scholar ↗

2024

LipSim: A Provably Robust Perceptual Similarity Metric

Sara Ghazanfari, Alexandre Araujo, Prashanth Krishnamurthy, Farshad Khorrami, Siddharth Garg

ICLR 2024poster

Recent years have seen growing interest in developing and applying perceptual similarity metrics. Research has shown the superiority of perceptual metrics over pixel-wise metrics in aligning with human perception and serving as a proxy for the human visual system. On the other hand, as perceptual me…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗

2024

NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security

Minghao Shao, Sofija Jancheska, Meet Udeshi, Brendan Dolan-Gavitt, Haoran Xi, Kimberly Milner +7

NeurIPS 2024poster

Large Language Models (LLMs) are being deployed across various domains today. However, their capacity to solve Capture the Flag (CTF) challenges in cybersecurity has not been thoroughly evaluated. To address this, we develop a novel method to assess LLMs in solving CTF challenges by creating a scala…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗

2024

Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations

Patricia Pauli, Aaron J Havens, Alexandre Araujo, Siddharth Garg, Farshad Khorrami, Frank Allgöwer +1

ICLR 2024poster

Recently, semidefinite programming (SDP) techniques have shown great promise in providing accurate Lipschitz bounds for neural networks. Specifically, the LipSDP approach (Fazlyab et al., 2019) has received much attention and provides the least conservative Lipschitz upper bounds that can be compute…

Cited by 6 Source ↗PDF ↗Scholar ↗

2024

On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem

Georg Pichler, Marco Romanelli, Divya Prakash Manivannan, Prashanth Krishnamurthy, Farshad khorrami, Siddharth Garg

AISTATS 2024poster

We introduce a formal statistical definition for the problem of backdoor detection in machine learning systems and use it to analyze the feasibility of such problems, providing evidence for the utility and applicability of our definition. The main contributions of this work are an impossibility resu…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗

2024

SALSA: Swift Adaptive Lightweight Self-Attention for Enhanced LiDAR Place Recognition

Raktim Gautam Goswami, Naman Patel, Prashanth Krishnamurthy, Farshad Khorrami

RA-L 2024

Large-scale LiDAR mappings and localization leverage place recognition techniques to mitigate odometry drifts, ensuring accurate mapping. These techniques utilize scene representations from LiDAR point clouds to identify previously visited sites within a database. Local descriptors, assigned to each

Cited by 10 Source ↗code ↗Scholar ↗

2024

Sailing Through Point Clouds: Safe Navigation Using Point Cloud Based Control Barrier Functions

Bolun Dai, Rooholla Khorrambakht, Prashanth Krishnamurthy, Farshad Khorrami

RA-L 2024

The capability to navigate safely in an unstructured environment is crucial when deploying robotic systems in real-world scenarios. Recently, control barrier function (CBF) based approaches have been highly effective in synthesizing safety-critical controllers. In this letter, we propose a novel CBF

Cited by 11 Source ↗Scholar ↗

2023

Exploiting Connections between Lipschitz Structures for Certifiably Robust Deep Equilibrium Models

Aaron J Havens, Alexandre Araujo, Siddharth Garg, Farshad Khorrami, Bin Hu

NeurIPS 2023poster

Recently, deep equilibrium models (DEQs) have drawn increasing attention from the machine learning community. However, DEQs are much less understood in terms of certified robustness than their explicit network counterparts. In this paper, we advance the understanding of certified robustness of DEQs…

Cited by 10 Source ↗PDF ↗code ↗Scholar ↗

2023

Safe Navigation and Obstacle Avoidance Using Differentiable Optimization Based Control Barrier Functions

Bolun Dai, Rooholla Khorrambakht, Prashanth Krishnamurthy, Vinicius Mariano Gonçalves, Anthony Tzes, Farshad Khorrami

RA-L 2023

Control barrier functions (CBFs) have been widely applied to safety-critical robotic applications. However, the construction of control barrier functions for robotic systems remains a challenging task. Recently, collision detection using differentiable optimization has provided a way to compute the

Cited by 52 Source ↗Scholar ↗

2023

Towards better certified segmentation via diffusion models

Othmane Laousy, Alexandre Araujo, Guillaume Chassagnon, Marie-Pierre Revel, Siddharth Garg, Farshad Khorrami +1

UAI 2023poster

The robustness of image segmentation has been an important research topic in the past few years as segmentation models have reached production-level accuracy. However, like classification models, segmentation models can be vulnerable to adversarial perturbations, which hinders their use in critical-…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2019

Adaptive Adversarial Videos on Roadside Billboards: Dynamically Modifying Trajectories of Autonomous Vehicles

Naman Patel, Prashanth Krishnamurthy, Siddharth Garg, Farshad Khorrami

IROS 2019poster

Deep neural networks (DNNs) are being incorporated into various autonomous systems like self-driving cars and robots. However, there is a rising concern about the robustness of these systems because of their susceptibility to adversarial attacks on DNNs. Past research has established that DNNs used…

Cited by 21 Source ↗Scholar ↗

2019

Sliding-Window Temporal Attention Based Deep Learning System for Robust Sensor Modality Fusion for UGV Navigation

Halil Utku Unlu, Naman Patel, Prashanth Krishnamurthy, Farshad Khorrami

RA-L 2019

We propose a novel temporal attention based neural network architecture for robotics tasks that involve fusion of time series of sensor data, and evaluate the performance improvements in the context of autonomous navigation of unmanned ground vehicles (UGVs) in uncertain environments. The architectu

Cited by 10 Source ↗Scholar ↗

2018

Adversarial Learning-Based On-Line Anomaly Monitoring for Assured Autonomy

Naman Patel, Apoorva Nandini Saridena, Anna Choromanska, Prashanth Krishnamurthy, Farshad Khorrami

IROS 2018poster

The paper proposes an on-line monitoring framework for continuous real-time safety/security in learning-based control systems (specifically application to a unmanned ground vehicle). We monitor validity of mappings from sensor inputs to actuator commands, controller-focused anomaly detection (CFAM),…

Cited by 29 Source ↗Scholar ↗

2017

Sensor modality fusion with CNNs for UGV autonomous driving in indoor environments

Naman Patel, Anna Choromanska, Prashanth Krishnamurthy, Farshad Khorrami

IROS 2017poster

We present a novel end-to-end learning framework to enable ground vehicles to autonomously navigate unknown environments by fusing raw pixels from cameras and depth measurements from a LiDAR. A deep neural network architecture is introduced to effectively perform modality fusion and reliably predict…

Cited by 78 Source ↗Scholar ↗

2015

Trunk stabilization of multi-legged robots using on-line learning via a NARX neural network compensator

Brian R. Cairl, Farshad Khorrami

IROS 2015poster

The objective of this work is to achieve disturbance rejection and constant orientation of the trunk of a multi-legged robot. This is significant when payloads (such as cameras, optical systems, armaments) are carried by the robot. In particular, this paper presents an application of an on-line lear…

Cited by 1 Source ↗Scholar ↗