arXiv subjects

Shubham Goel

Publications and source records attributed to Shubham Goel.

11 recordsLinked to original sources

arXiv2026

Orchestrating Specialized Agents for Trustworthy Enterprise RAG

Retrieval-Augmented Generation (RAG) shows promise for enterprise knowledge work, yet it often underperforms in high-stakes decision settings that require deep synthesis, strict traceability, and recovery from underspecified prompts. One-pass retrieval-and-write pipelines frequently yield shallow summaries, inconsistent grounding, and weak mechanisms for completeness verification. We introduce ADORE (Adaptive Deep Orchestration for Research in Enterprise), an agentic framework that replaces linear retrieval with iterative, user-steered investigation coordinated by a central orchestrator and a set of specialized agents. ADORE's key insight is that a structured Memory Bank (a curated evidence store with explicit claim-evidence linkage and section-level admissible evidence) enables traceable report generation and systematic checks for evidence completeness. Our contributions are threefold: (1) Memory-locked synthesis - report generation is constrained to a structured Memory Bank (Claim-Evidence Graph) with section-level admissible evidence, enabling traceable claims and grounded citations; (2) Evidence-coverage-guided execution - a retrieval-reflection loop audits section-level evidence coverage to trigger targeted follow-up retrieval and terminates via an evidence-driven stopping criterion; (3) Section-packed long-context grounding - section-level packing, pruning, and citation-preserving compression make long-form synthesis feasible under context limits. Across our evaluation suite, ADORE ranks first on DeepResearch Bench (52.65) and achieves the highest head-to-head preference win rate on DeepConsult (77.2%) against commercial systems.

cs.IR↗

arXiv2026

How Does India Cook Biryani?

Biryani, one of India's most celebrated dishes, exhibits remarkable regional diversity in its preparation, ingredients, and presentation. With the growing availability of online cooking videos, there is unprecedented potential to study such culinary variations using computational tools systematically. However, existing video understanding methods fail to capture the fine-grained, multimodal, and culturally grounded differences in procedural cooking videos. This work presents the first large-scale, curated dataset of biryani preparation videos, comprising 120 high-quality YouTube recordings across 12 distinct regional styles. We propose a multi-stage framework leveraging recent advances in vision-language models (VLMs) to segment videos into fine-grained procedural units and align them with audio transcripts and canonical recipe text. Building on these aligned representations, we introduce a video comparison pipeline that automatically identifies and explains procedural differences between regional variants. We construct a comprehensive question-answer (QA) benchmark spanning multiple reasoning levels to evaluate procedural understanding in VLMs. Our approach employs multiple VLMs in complementary roles, incorporates human-in-the-loop verification for high-precision tasks, and benchmarks several state-of-the-art models under zero-shot and fine-tuned settings. The resulting dataset, comparison methodology, and QA benchmark provide a new testbed for evaluating VLMs on structured, multimodal reasoning tasks and open new directions for computational analysis of cultural heritage through cooking videos. We release all data, code, and the project website at https://farzanashaju.github.io/how-does-india-cook-biryani/.

cs.CV↗

arXiv2024

Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind

As humans move around, performing their daily tasks, they are able to recall where they have positioned objects in their environment, even if these objects are currently out of their sight. In this paper, we aim to mimic this spatial cognition ability. We thus formulate the task of Out of Sight, Not Out of Mind - 3D tracking active objects using observations captured through an egocentric camera. We introduce a simple but effective approach to address this challenging problem, called Lift, Match, and Keep (LMK). LMK lifts partial 2D observations to 3D world coordinates, matches them over time using visual appearance, 3D location and interactions to form object tracks, and keeps these object tracks even when they go out-of-view of the camera. We benchmark LMK on 100 long videos from EPIC-KITCHENS. Our results demonstrate that spatial cognition is critical for correctly locating objects over short and long time scales. E.g., for one long egocentric video, we estimate the 3D location of 50 active objects. After 120 seconds, 57% of the objects are correctly localised by LMK, compared to just 33% by a recent 3D method for egocentric videos and 17% by a general 2D tracking method.

cs.CV↗

arXiv2024

The More You See in 2D, the More You Perceive in 3D

Humans can infer 3D structure from 2D images of an object based on past experience and improve their 3D understanding as they see more images. Inspired by this behavior, we introduce SAP3D, a system for 3D reconstruction and novel view synthesis from an arbitrary number of unposed images. Given a few unposed images of an object, we adapt a pre-trained view-conditioned diffusion model together with the camera poses of the images via test-time fine-tuning. The adapted diffusion model and the obtained camera poses are then utilized as instance-specific priors for 3D reconstruction and novel view synthesis. We show that as the number of input images increases, the performance of our approach improves, bridging the gap between optimization-based prior-less 3D reconstruction methods and single-image-to-3D diffusion-based methods. We demonstrate our system on real images as well as standard synthetic benchmarks. Our ablation studies confirm that this adaption behavior is key for more accurate 3D understanding.

cs.CV↗

arXiv2023

Humans in 4D: Reconstructing and Tracking Humans with Transformers

We present an approach to reconstruct humans and track them over time. At the core of our approach, we propose a fully "transformerized" version of a network for human mesh recovery. This network, HMR 2.0, advances the state of the art and shows the capability to analyze unusual poses that have in the past been difficult to reconstruct from single images. To analyze video, we use 3D reconstructions from HMR 2.0 as input to a tracking system that operates in 3D. This enables us to deal with multiple people and maintain identities through occlusion events. Our complete approach, 4DHumans, achieves state-of-the-art results for tracking people from monocular video. Furthermore, we demonstrate the effectiveness of HMR 2.0 on the downstream task of action recognition, achieving significant improvements over previous pose-based action recognition approaches. Our code and models are available on the project website: https://shubham-goel.github.io/4dhumans/.

cs.CV↗

arXiv2021

ABO: Dataset and Benchmarks for Real-World 3D Object Understanding

We introduce Amazon Berkeley Objects (ABO), a new large-scale dataset designed to help bridge the gap between real and virtual 3D worlds. ABO contains product catalog images, metadata, and artist-created 3D models with complex geometries and physically-based materials that correspond to real, household objects. We derive challenging benchmarks that exploit the unique properties of ABO and measure the current limits of the state-of-the-art on three open problems for real-world 3D object understanding: single-view 3D reconstruction, material estimation, and cross-domain multi-view object retrieval.

cs.CV↗

arXiv2021

Differentiable Stereopsis: Meshes from multiple views using differentiable rendering

We propose Differentiable Stereopsis, a multi-view stereo approach that reconstructs shape and texture from few input views and noisy cameras. We pair traditional stereopsis and modern differentiable rendering to build an end-to-end model which predicts textured 3D meshes of objects with varying topologies and shape. We frame stereopsis as an optimization problem and simultaneously update shape and cameras via simple gradient descent. We run an extensive quantitative analysis and compare to traditional multi-view stereo techniques and state-of-the-art learning based methods. We show compelling reconstructions on challenging real-world scenes and for an abundance of object types with complex shape, topology and texture. Project webpage: https://shubham-goel.github.io/ds/

cs.CV↗

arXiv2020

Shape and Viewpoint without Keypoints

We present a learning framework that learns to recover the 3D shape, pose and texture from a single image, trained on an image collection without any ground truth 3D shape, multi-view, camera viewpoints or keypoint supervision. We approach this highly under-constrained problem in a "analysis by synthesis" framework where the goal is to predict the likely shape, texture and camera viewpoint that could produce the image with various learned category-specific priors. Our particular contribution in this paper is a representation of the distribution over cameras, which we call "camera-multiplex". Instead of picking a point estimate, we maintain a set of camera hypotheses that are optimized during training to best explain the image given the current shape and texture. We call our approach Unsupervised Category-Specific Mesh Reconstruction (U-CMR), and present qualitative and quantitative results on CUB, Pascal 3D and new web-scraped datasets. We obtain state-of-the-art camera prediction results and show that we can learn to predict diverse shapes and textures across objects using an image collection without any keypoint annotations or 3D ground truth. Project page: https://shubham-goel.github.io/ucmr

cs.CV↗

arXiv2019

Identifying short-term interests from mobile app adoption pattern

With the increase in an average user's dependence on their mobile devices, the reliance on collecting his browsing history from mobile browsers has also increased. This browsing history is highly utilized in the advertising industry for providing targeted ads in the purview of inferring his short-term interests and pushing relevant ads. However, the major limitation of such an extraction from mobile browsers is that they reset when the browser is closed or when the device is shut down/restarted; thus rendering existing methods to identify the user's short-term interests on mobile devices users, ineffective. In this paper, we propose an alternative method to identify such short-term interests by analysing their mobile app adoption (installation/uninstallation) patterns over a period of time. Such a method can be highly effective in pinpointing the user's ephemeral inclinations like buying/renting an apartment, buying/selling a car or a sudden increased interest in shopping (possibly due to a recent salary bonus, he received). Subsequently, these derived interests are also used for targeted experiments. Our experiments result in up to 93.68% higher click-through rate in comparison to the ads shown without any user-interest knowledge. Also, up to 51% higher revenue in the long term is expected as a result of the application of our proposed algorithm.

cs.IR↗

arXiv2018

What's hard about Boolean Functional Synthesis

Given a relational specification between Boolean inputs and outputs, the goal of Boolean functional synthesis is to synthesize each output as a function of the inputs such that the specification is met. In this paper, we first show that unless some hard conjectures in complexity theory are falsified, Boolean functional synthesis must necessarily generate exponential-sized Skolem functions, thereby requiring exponential time, in the worst-case. Given this inherent hardness, what does one do to solve the problem? We present a two-phase algorithm for Boolean functional synthesis, where the first phase is efficient both in terms of time and sizes of synthesized functions, and solves an overwhelming majority of benchmarks. To explain this surprisingly good performance, we provide a sufficient condition under which the first phase must produce exact correct answers. When this condition fails, the second phase builds upon the result of the first phase, possibly requiring exponential time and generating exponential-sized functions in the worst-case. Detailed experimental evaluation shows our algorithm to perform better than state-of-the-art techniques for a majority of benchmarks.

cs.LO↗

arXiv2017

Computing Scores of Forwarding Schemes in Switched Networks with Probabilistic Faults

Time-triggered switched networks are a deterministic communication infrastructure used by real-time distributed embedded systems. Due to the criticality of the applications running over them, developers need to ensure that end-to-end communication is dependable and predictable. Traditional approaches assume static networks that are not flexible to changes caused by reconfigurations or, more importantly, faults, which are dealt with in the application using redundancy. We adopt the concept of handling faults in the switches from non-real-time networks while maintaining the required predictability. We study a class of forwarding schemes that can handle various types of failures. We consider probabilistic failures. For a given network with a forwarding scheme and a constant $\ell$, we compute the {\em score} of the scheme, namely the probability (induced by faults) that at least $\ell$ messages arrive on time. We reduce the scoring problem to a reachability problem on a Markov chain with a "product-like" structure. Its special structure allows us to reason about it symbolically, and reduce the scoring problem to #SAT. Our solution is generic and can be adapted to different networks and other contexts. Also, we show the computational complexity of the scoring problem is #P-complete, and we study methods to estimate the score. We evaluate the effectiveness of our techniques with an implementation.

cs.DC↗