collaborators

6 papers

cs.CV2026

Mitigating Hallucination in Vision-Language Models through Barrier-Regulated Adaptive Closed-form Steering

Soumyadeep Jana, Pulkit Mittal, Sanasam Ranbir Singh

Large vision-language models (LVLMs) often hallucinate objects that are not present in the input image, largely because visual grounding weakens as decoding progresses. Existing in…

cs.AI2026

Moment-KV: Momentum-Based Decode-Time KV Cache Compression for Long Generation

Soumyadeep Jana, Sagar Nishad, Sanasam Ranbir Singh

Key-Value (KV) cache remains a major bottleneck for deploying Large Language Models (LLMs) in long-generation tasks. Prior work often applies uniform compression across both prefil…

cs.CL2025

Teaching Sarcasm: Few-Shot Multimodal Sarcasm Detection via Distillation to a Parameter-Efficient Student

Soumyadeep Jana, Sanasam Ranbir Singh

Multimodal sarcasm detection is challenging, especially in low-resource settings where subtle image-text contradictions are hard to learn due to scarce annotated data, which hinder…

cs.CL2025

Adapter-state Sharing CLIP for Parameter-efficient Multimodal Sarcasm Detection

Soumyadeep Jana, Sahil Danayak, Sanasam Ranbir Singh

The growing prevalence of multimodal image-text sarcasm on social media poses challenges for opinion mining systems. Existing approaches rely on full fine-tuning of large models, m…

cs.CL2025

Think Twice Before You Judge: Mixture of Dual Reasoning Experts for Multimodal Sarcasm Detection

Soumyadeep Jana, Abhrajyoti Kundu, Sanasam Ranbir Singh

Multimodal sarcasm detection has attracted growing interest due to the rise of multimedia posts on social media. Understanding sarcastic image-text posts often requires external co…

cs.CL2025

Dual Modality-Aware Gated Prompt Tuning for Few-Shot Multimodal Sarcasm Detection

Soumyadeep Jana, Abhrajyoti Kundu, Sanasam Ranbir Singh

The widespread use of multimodal content on social media has heightened the need for effective sarcasm detection to improve opinion mining. However, existing models rely heavily on…