AIConfPaper
← Search

Apoorv Saxena

12 accepted papers

2026

FlowCast: Trajectory Forecasting for Scalable Zero-Cost Speculative Flow Matching

Divya Jyoti Bajpai, Shubham Agarwal, Apoorv Saxena, Kuldeep Kulkarni, Subrata Mitra, Manjesh Kumar Hanawal
ICLR 2026poster

Flow Matching (FM) has recently emerged as a powerful approach for high-quality visual generation. However, their prohibitively slow inference due to a large number of denoising steps limits their potential use in real-time or interactive applications. Existing acceleration methods, like distillatio…

Cited by 0Source ↗Scholar ↗
2025

Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs

Anirudh Phukan, Divyansh Divyansh, Harshit Kumar Morj, Vaishnavi Vaishnavi, Apoorv Saxena, Koustava Goswami
NAACL 2025long

The rapid development of Large Multimodal Models (LMMs) has significantly advanced multimodal understanding by harnessing the language abilities of Large Language Models (LLMs) and integrating modality-specific encoders. However, LMMs are plagued by hallucinations that limit their reliability and ad…

Cited by 1Source ↗PDF ↗Scholar ↗
2025

Doc2Chart: Intent-Driven Zero-Shot Chart Generation from Documents

Akriti Jain, Pritika Ramu, Aparna Garimella, Apoorv Saxena
EMNLP 2025

Large Language Models (LLMs) have demonstrated strong capabilities in transforming text descriptions or tables to data visualizations via instruction-tuning methods. However, it is not straightforward to apply these methods directly for a more real-world use case of visualizing data from long docume

Cited by 0Source ↗PDF ↗Scholar ↗
2025

PLD+: Accelerating LLM Inference by Leveraging Language Model Artifacts

Shwetha Somasundaram, Anirudh Phukan, Apoorv Saxena
NAACL 2025findings

To reduce the latency associated with autoretrogressive LLM inference, speculative decoding has emerged as a novel decoding paradigm, where future tokens are drafted and verified in parallel. However, the practical deployment of speculative decoding is hindered by its requirements for additional com…

Cited by 1Source ↗PDF ↗Scholar ↗
2024

A Tale of Two Revisions: Summarizing Changes Across Document Versions

Santosh T.y.s.s, Natwar Modani, Apoorv Saxena
ACL 2024findings

Document revision is a crucial aspect of the writing process, particularly in collaborative environments where multiple authors contribute simultaneously. However, current tools lack an efficient way to provide a comprehensive overview of changes between versions, leading to difficulties in understa…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decomposition

Pritika Ramu, Koustava Goswami, Apoorv Saxena, Balaji Vasan Srinivasan
EMNLP 2024main

Accurately attributing answer text to its source document is crucial for developing a reliable question-answering system. However, attribution for long documents remains largely unexplored. Post-hoc attribution systems are designed to map answer text back to the source document, yet the granularity…

Cited by 3Source ↗PDF ↗Scholar ↗
2024

Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering

Anirudh Phukan, Shwetha Somasundaram, Apoorv Saxena, Koustava Goswami, Balaji Vasan Srinivasan
ACL 2024findings

With the enhancement in the field of generative artificial intelligence (AI), contextual question answering has become extremely relevant. Attributing model generations to the input source document is essential to ensure trustworthiness and reliability. We observe that when large language models (LL…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2023

A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis

Aishwarya Agarwal, Srikrishna Karanam, K J Joseph, Apoorv Saxena, Koustava Goswami, Balaji Vasan Srinivasan
ICCV 2023poster

While recent developments in text-to-image generative models have led to a suite of high-performing methods capable of producing creative imagery from free-form text, there are several limitations. By analyzing the cross-attention representations of these models, we notice two key issues. First, for…

Cited by 44PDF ↗Scholar ↗
2023

Drilling Down into the Discourse Structure with LLMs for Long Document Question Answering

Inderjeet Jayakumar Nair, Shwetha S, Apoorv Saxena, Koustava Goswami
EMNLP 2023long findings

We address the task of evidence retrieval for long document question answering, which involves locating relevant paragraphs within a document to answer a question. We aim to assess the applicability of large language models (LLMs) in the task of zero-shot long document evidence retrieval, owing to t…

Cited by 0Source ↗Scholar ↗
2023

Open-World Factually Consistent Question Generation

Himanshu Maheshwari, Sumit Shekhar, Apoorv Saxena, Niyati Chhaya
ACL 2023findings

Question generation methods based on pre-trained language models often suffer from factual inconsistencies and incorrect entities and are not answerable from the input paragraph. Domain shift – where the test data is from a different domain than the training data - further exacerbates the problem of…

Cited by 4Source ↗PDF ↗Scholar ↗
2022

Sequence-to-Sequence Knowledge Graph Completion and Question Answering

Apoorv Saxena, Adrian Kochsiek, Rainer Gemulla
ACL 2022long

Knowledge graph embedding (KGE) models represent each entity and relation of a knowledge graph (KG) with low-dimensional embedding vectors. These methods have recently been applied to KG link prediction and question answering over incomplete KGs (KGQA). KGEs typically create an embedding for each en…

Cited by 191Source ↗PDF ↗code ↗Scholar ↗