Papers by Tanmana Sadhu

4 papers
Open-World Planning via Lifted Regression with LLM-Inferred Affordances for Embodied Agents (2025.acl-long)

Copied to clipboard

Challenge: Existing open-world planning methods rely on closed-world assumption (CWA) symbolic planners face combinatorial explosion of states and actions due to reliance on grounding.
Approach: They propose an open-world planning approach integrating lifted regression with LLM-generated affordances.
Outcome: The proposed approach outperforms state-of-the-art LLM planners and a grounded planner on three benchmarks.
Athena: Safe Autonomous Agents with Verbal Contrastive Learning (2024.emnlp-industry)

Copied to clipboard

Challenge: Existing safety benchmarks on the ability of large language models to perform tasks are lacking.
Approach: They propose a framework that leverages verbal contrastive learning to guide agents towards safety . they use past safe and unsafe trajectories as in-context examples to guide them towards safety.
Outcome: The proposed framework leverages verbal contrastive learning to guide agents towards safety while performing tasks.
VestaBench: An Embodied Benchmark for Safe Long-Horizon Planning Under Multi-Constraint and Adversarial Settings (2025.emnlp-industry)

Copied to clipboard

Challenge: Existing safety benchmarks do not represent a diverse range of multi-constraint tasks that require long-horizon planning with a focus on safety.
Approach: They propose a benchmark to assess the safety of embodied AI agents under multiple constraints.
Outcome: The proposed benchmarks show that LLMs perform poorly against their tasks . they also suffer significantly compromised safety outcomes .
Exploring Compositional Image Retrieval with Hybrid Compositional Learning and Heuristic Negative Mining (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing CIR models are pre-trained on uni-modal data, resulting in unimodal data.
Approach: They propose a CIR model HyCoLe-HNM with CLIP as the backbone . they use a gated fusion mechanism from a question answering model to perform compositional learning .
Outcome: The proposed model achieves state-of-the-art performance on three CIR datasets . it borrows a gated fusion mechanism from a question answering model to perform compositional fusion .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations