7 citations · 14 across the 30 of their papers we have counts for
30 papers
Spurious Advantage Hidden in GRPO
Jiamian Wang, Samyadeep Basu, Koustava Goswami +2
Group Relative Policy Optimization (GRPO) is widely studied for reinforcement learning with verifiable rewards, where its advantage estimator assigns each rollout a magnitude from…
A Glance Is All You Need: Single-Pass Fine-Grained Image Captioning with SimLoss
Suryaansh Jain, Rahasya Barkur, Vishal G +8
An image may be worth a thousand words, but most captioning models describe it in only a few. Modern vision-language models produce fluent high-level captions, yet routinely miss t…
MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering
Dang Quang Thien Tran, Quang V. Dang, Vinamra Tyagi +7
As grounded QA systems are increasingly deployed in AI assistants, accurately attributing generated answers to evidence is critical for user trust and model safety. While unimodal…
RL-Index: Reinforcement Learning for Retrieval Index Reasoning
Yongjia Lei, Nedim Lipka, Zhisheng Qi +7
Retrieving external knowledge is crucial for real-world tasks but remains difficult when queries and relevant knowledge are linked by implicit reasoning (e.g., shared theorems or c…
FLARE: Diffusion for Hybrid Language Model
Yuchen Zhu, Jing Shi, Chongjian Ge +9
Autoregressive (AR) large language models (LLMs) have achieved broad practical success, but sequential decoding remains a key bottleneck for low-latency deployment. Recent efficien…
Enhancing Multilingual Embeddings via Multi-Way Parallel Text Alignment
Barah Fazili, Koustava Goswami
Multilingual pretraining typically lacks explicit alignment signals, leading to suboptimal cross-lingual alignment in the representation space. In this work, we show that training…
Human-Aligned MLLM Judges for Fine-Grained Image Editing Evaluation: A Benchmark, Framework, and Analysis
Runzhou Liu, Hailey Weingord, Sejal Mittal +18
Evaluating image editing models remains challenging due to the coarse granularity and limited interpretability of traditional metrics, which often fail to capture aspects important…
SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG
Xuechen Zhang, Koustava Goswami, Samet Oymak +2
Retrieval-augmented generation (RAG) has strong potential for producing accurate and factual outputs by combining language models (LMs) with evidence retrieved from large text corp…
Step-by-step Layered Design Generation
Faizan Farooq Khan, K J Joseph, Koustava Goswami +2
Design generation, in its essence, is a step-by-step process where designers progressively refine and enhance their work through careful modifications. Despite this fundamental cha…
Decomposition-Enhanced Training for Post-Hoc Attributions In Language Models
Sriram Balasubramanian, Samyadeep Basu, Koustava Goswami +6
Large language models (LLMs) are increasingly used for long-document question answering, where reliable attribution to sources is critical for trust. Existing post-hoc attribution…
Subjective Behaviors and Preferences in LLM: Language of Browsing
Sai Sundaresan, Harshita Chopra, Atanu R. Sinha +4
A Large Language Model (LLM) offers versatility across domains and tasks, purportedly benefiting users with a wide variety of behaviors and preferences. We question this perception…
Do It Yourself (DIY): Modifying Images for Poems in a Zero-Shot Setting Using Weighted Prompt Manipulation
Sofia Jamil, Kotla Sai Charan, Sriparna Saha +2
Poetry is an expressive form of art that invites multiple interpretations, as readers often bring their own emotions, experiences, and cultural backgrounds into their understanding…
Agentic Design Review System
Sayan Nag, K J Joseph, Koustava Goswami +2
Evaluating graphic designs involves assessing it from multiple facets like alignment, composition, aesthetics and color choices. Evaluating designs in a holistic way involves aggre…
PoemTale Diffusion: Minimising Information Loss in Poem to Image Generation with Multi-Stage Prompt Refinement
Sofia Jamil, Bollampalli Areen Reddy, Raghvendra Kumar +3
Recent advancements in text-to-image diffusion models have achieved remarkable success in generating realistic and diverse visual content. A critical factor in this process is the…
Poetry in Pixels: Prompt Tuning for Poem Image Generation via Diffusion Models
Sofia Jamil, Bollampalli Areen Reddy, Raghvendra Kumar +3
The task of text-to-image generation has encountered significant challenges when applied to literary works, especially poetry. Poems are a distinct form of literature, with meaning…
Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs
Anirudh Phukan, Divyansh, Harshit Kumar Morj +3
The rapid development of Large Multimodal Models (LMMs) has significantly advanced multimodal understanding by harnessing the language abilities of Large Language Models (LLMs) and…
Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decomposition
Pritika Ramu, Koustava Goswami, Apoorv Saxena +1
Accurately attributing answer text to its source document is crucial for developing a reliable question-answering system. However, attribution for long documents remains largely un…
GenSco: Can Question Decomposition based Passage Alignment improve Question Answering?
Barah Fazili, Koustava Goswami, Natwar Modani +1
Retrieval augmented generation (RAG) with large language models (LLMs) for Question Answering (QA) entails furnishing relevant context within the prompt to facilitate the LLM in an…
SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation
Sayan Nag, Koustava Goswami, Srikrishna Karanam
Referring Expression Segmentation (RES) aims to provide a segmentation mask of the target object in an image referred to by the text (i.e., referring expression). Existing methods…
Post-Hoc Answer Attribution for Grounded and Trustworthy Long Document Comprehension: Task, Insights, and Challenges
Abhilasha Sancheti, Koustava Goswami, Balaji Vasan Srinivasan
Attributing answer text to its source document for information-seeking questions is crucial for building trustworthy, reliable, and accountable systems. We formulate a new task of…
Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering
Anirudh Phukan, Shwetha Somasundaram, Apoorv Saxena +2
With the enhancement in the field of generative artificial intelligence (AI), contextual question answering has become extremely relevant. Attributing model generations to the inpu…
An Audit on the Perspectives and Challenges of Hallucinations in NLP
Pranav Narayanan Venkit, Tatiana Chakravorti, Vipul Gupta +5
We audit how hallucination in large language models (LLMs) is characterized in peer-reviewed literature, using a critical examination of 103 publications across NLP research. Throu…
Social Media Ready Caption Generation for Brands
Himanshu Maheshwari, Koustava Goswami, Apoorv Saxena +1
Social media advertisements are key for brand marketing, aiming to attract consumers with captivating captions and pictures or logos. While previous research has focused on generat…
Drilling Down into the Discourse Structure with LLMs for Long Document Question Answering
Inderjeet Nair, Shwetha Somasundaram, Apoorv Saxena +1
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…