GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards.

Pala Tej Deep https://orcid.org/0009-0002-6741-2379

Pala Tej Deep Vernon Toh Soujanya Poria GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards. 2026 June abs/2606.04889 CoRR https://doi.org/10.48550/arXiv.2606.04889 db/journals/corr/corr2606.html#abs-2606-04889 streams/journals/corr

Qi Sun Pengfei Hong Pala Tej Deep Vernon Toh U-Xuan Tan Deepanway Ghosal Soujanya Poria Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning. 14199-14214 2025 ACL (1) https://doi.org/10.18653/v1/2025.acl-long.695 https://aclanthology.org/2025.acl-long.695/ conf/acl/2025-1 db/conf/acl/acl2025-1.html#SunHDTTGP25 Pala Tej Deep Vernon Toh Rishabh Bhardwaj Soujanya Poria Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique. EMNLP (Findings) 2025 11845-11860 conf/emnlp/2025f https://doi.org/10.18653/v1/2025.findings-emnlp.634 https://aclanthology.org/2025.findings-emnlp.634/ db/conf/emnlp/emnlp2025f.html#DeepTBP25 streams/conf/emnlp Pala Tej Deep Panshul Sharma Amir Zadeh 0001 Chuan Li Soujanya Poria Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision. EMNLP (Findings) 2025 14940-14954 conf/emnlp/2025f https://doi.org/10.18653/v1/2025.findings-emnlp.807 https://aclanthology.org/2025.findings-emnlp.807/ db/conf/emnlp/emnlp2025f.html#DeepSZLP25 streams/conf/emnlp

Weisheng Jin Maojia Song Pala Tej Deep Yew Ken Chia Amir Zadeh 0001 Chuan Li Soujanya Poria PromptDistill: Query-based Selective Token Retention in Intermediate Layers for Efficient Large Language Model Inference. 2025 March abs/2503.23274 CoRR https://doi.org/10.48550/arXiv.2503.23274 db/journals/corr/corr2503.html#abs-2503-23274 streams/journals/corr

Pala Tej Deep Panshul Sharma Amir Zadeh 0001 Chuan Li Soujanya Poria Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision. 2025 May abs/2505.19706 CoRR https://doi.org/10.48550/arXiv.2505.19706 db/journals/corr/corr2505.html#abs-2505-19706 streams/journals/corr

Shang Hong Sim Pala Tej Deep Vernon Toh Hai Leong Chieu Amir Zadeh 0001 Chuan Li Navonil Majumder Soujanya Poria Lessons from Training Grounded LLMs with Verifiable Rewards. 2025 June abs/2506.15522 CoRR https://doi.org/10.48550/arXiv.2506.15522 db/journals/corr/corr2506.html#abs-2506-15522 streams/journals/corr

Maojia Song Pala Tej Deep Weisheng Jin Amir Zadeh 0001 Chuan Li Dorien Herremans Soujanya Poria LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactions. 2025 August abs/2508.18321 CoRR https://doi.org/10.48550/arXiv.2508.18321 db/journals/corr/corr2508.html#abs-2508-18321 streams/journals/corr

Brandon Ong Pala Tej Deep Vernon Toh William-Chandra Tjhi Soujanya Poria Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned. 2025 September abs/2509.23250 CoRR https://doi.org/10.48550/arXiv.2509.23250 db/journals/corr/corr2509.html#abs-2509-23250 streams/journals/corr

Pala Tej Deep Rishabh Bhardwaj Soujanya Poria DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling. 2024 abs/2406.11617 CoRR https://doi.org/10.48550/arXiv.2406.11617 db/journals/corr/corr2406.html#abs-2406-11617 streams/journals/corr

Pala Tej Deep Vernon Toh Yan Han Rishabh Bhardwaj Soujanya Poria Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique. 2024 abs/2408.10701 CoRR https://doi.org/10.48550/arXiv.2408.10701 db/journals/corr/corr2408.html#abs-2408-10701 streams/journals/corr

Qi Sun Pengfei Hong Pala Tej Deep Vernon Toh U-Xuan Tan Deepanway Ghosal Soujanya Poria Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning. 2024 abs/2412.11974 CoRR https://doi.org/10.48550/arXiv.2412.11974 db/journals/corr/corr2412.html#abs-2412-11974 streams/journals/corr

Rishabh Bhardwaj Yew Ken Chia Hai Leong Chieu Deepanway Ghosal Vernon Toh Yan HanVernon Toh Dorien Herremans Pengfei Hong Weisheng Jin Chuan Li Navonil Majumder Brandon Ong Soujanya Poria Panshul Sharma Shang Hong Sim Maojia Song Qi Sun U-Xuan Tan William-Chandra Tjhi Amir Zadeh 0001