Papers by Prashanth Vijayaraghavan
CODMAS: A Dialectic Multi-Agent Collaborative Framework for Structured RTL Optimization (2026.eacl-industry)
Copied to clipboard
Che-Ming Chang, Prashanth Vijayaraghavan, Ashutosh Jadhav, Charles Mackin, Hsinyu Tsai, Vandana Mukherjee, Ehsan Degan
| Challenge: | generating and optimizing Hardware Description Languages (HDLs) remains challenging. |
| Approach: | They propose a framework that combines dialectic reasoning with domain-aware code generation and deterministic evaluation to automate RTL optimization. |
| Outcome: | The proposed framework reduces critical path delay and power loss by 25% compared to baselines. |
DAPPER: Learning Domain-Adapted Persona Representation Using Pretrained BERT and External Memory (2020.aacl-main)
Copied to clipboard
| Challenge: | Empirical evidence suggests that the learnt persona embeddings can be effective in downstream tasks like hate speech detection. |
| Approach: | They propose a model that embeds personas from natural language into text . they evaluate the transferability of the model by simulating low-resource scenarios . |
| Outcome: | The proposed model can learn to embed persona from natural language and alleviate task or domain-specific data sparsity issues related to personas. |
SYMDIREC: A Neuro-Symbolic Divide-Retrieve-Conquer Framework for Enhanced RTL Synthesis and Summarization (2026.eacl-industry)
Copied to clipboard
Prashanth Vijayaraghavan, Apoorva Nitsure, Luyao Shi, Charles Mackin, Ashutosh Jadhav, David Beymer, Ehsan Degan, Vandana Mukherjee
| Challenge: | Existing prompting and retrieval-augmented generation methods lack symbolic planning . rigid HDL syntax, limited supervision, and weak alignment with natural language hinder RTL synthesis and summarization. |
| Approach: | SYMDIREC decomposes RTL tasks into symbolic subgoals and assembles verified outputs . a neuro-symbolic framework supports both Verilog and VHDL without LLM fine-tuning . |
| Outcome: | SYMDIREC achieves higher Pass@1 rates for synthesis and 15–20% ROUGE-L improvements for summarization over prompting and RAG . synthesis, summarizing require preserving strict HDL syntax, modular structure, and precise functional semantics, authors show . |
TWEETSPIN: Fine-grained Propaganda Detection in Social Media Using Multi-View Representations (2022.naacl-main)
Copied to clipboard
| Challenge: | Recent studies on propaganda detection involve document and fragment-level analyses of news articles. |
| Approach: | They propose a neural approach to detect and categorize propaganda tweets across fine-grained categories . they use a dataset containing tweets weakly annotated with different propaganda techniques . |
| Outcome: | The proposed method outperforms benchmark methods and transfers knowledge to low-resource news domains. |
PROMINET: Prototype-based Multi-View Network for Interpretable Email Response Prediction (2023.emnlp-industry)
Copied to clipboard
| Challenge: | a new study examines email marketing performance by considering email content and metadata. |
| Approach: | They propose a model that incorporates semantic and structural information from email data to generate latent exemplars for email response prediction. |
| Outcome: | The proposed model outperforms baseline models on two real-world email datasets . it provides interpretability through prototypes at different granularity levels while maintaining comparable performance to non-interpretable models. |
Lifelong Knowledge-Enriched Social Event Representation Learning (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing approaches to represent social events and situations fail to consider pragmatic aspects . a conceptual framework for lifelong language learning integrates commonsense knowledge with lifelong learning. |
| Approach: | They propose a representation learning framework that integrates pragmatic aspects with lifelong language learning. |
| Outcome: | The proposed model integrates commonsense knowledge with lifelong language learning to produce richer representations of social events. |
Learning Personas from Dialogue with Attentive Memory Networks (D18-1)
Copied to clipboard
| Challenge: | Existing systems that can infer persona from dialogue can be used for computational narrative analysis and personalized dialogue generation. |
| Approach: | They propose neural models to learn persona embeddings in a character trope classification task using IMDB dialogue snippets. |
| Outcome: | The proposed methods could be applied to other domains, including personalized dialogue generation. |