3 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
Tracing Thought: Using Chain-of-Thought Reasoning to Identify the LLM Behind AI-Generated Text
Shifali Agrahari, Sanasam Ranbir Singh
In recent years, the detection of AI-generated text has become a critical area of research due to concerns about academic integrity, misinformation, and ethical AI deployment. This…