1.2k citations · 2.5k across the 147 of their papers we have counts for
167 papers
Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training
Suorong Yang, Jiaxin Wang, Jiaming Su +4
Large language models have achieved remarkable advances in complex reasoning. However, scaling reasoning post-training with ever-larger corpora can substantially increase training…
RoboQuest: Generalist Physical Agents that Search, Inspect and Test
Liu Renhang, Navonil Majumder, Tej Deep Pala +1
Recent advances in multimodal foundation models have made them capable generalist physical agents for a range of manipulation tasks. However, successful operation in an unfamiliar…
BaRe-Mem: Bayesian Reliability Memory for Robust and Adaptive Agent Consultation
Peilin Feng, Zhengyang Huang, Soujanya Poria
In multi-agent systems, reliable consultation is challenging because advisor capabilities vary across tasks, and misleading information can make consultation worse than autonomous…
Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models
Jingdi lei, Junxian Li, Di Zhang +3
Long visual token sequences often account for a substantial fraction of the computational overhead in multimodal large language models~(MLLMs). Existing approaches reduce this cost…
MemBodied: Recurrent Associative Memory for Vision-Language-Action Models
Tej Deep Pala, Navonil Majumder, Bryce Goh +4
Vision-Language-Action models provide a strong foundation for general-purpose robot control, yet a vast majority of policies do not preserve and leverage episode-level information…
GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation
AgiBot Research Team, Renhang Liu, Wenzhi Zhao +42
World-action models (WAM) predict future states to guide robot actions, enabling learning from both action-free video and action-labeled interaction. Most inherit pretrained video…
MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents
Vernon Toh, Navonil Majumder, Zhengyuan Liu +2
AI agents in partially observable environments need to coordinate active sensing with working memory to maintain an evolving perceptual state. However, existing benchmarks struggle…
ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step
Vernon Toh, Navonil Majumder, Zhengyuan Liu +2
To operate robustly in open-world environments, autonomous agents should be able to infer the behavior of unfamiliar systems through interaction alone, even in the absence of docum…
-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems
Peilin Feng, Suorong Yang, Soujanya Poria
Memory is central to long-horizon LLM agents, yet existing memory systems primarily preserve interaction content rather than modeling which agents can be trusted and under what con…
IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation
Varun Gumma, Navonil Majumder, Soumitra Sinhahajari +1
Large Language Models (LLMs) have significantly advanced the automation of scientific discovery. However, existing systems share a core limitation: they optimize ideas independentl…
On the Limits of LLM-as-Judge for Scientific Novelty Assessment
Soumitra Sinhahajari, Navonil Majumder, Soujanya Poria
LLMs are increasingly used to generate and judge scientific ideas. This makes novelty evaluation a central problem. Full idea evaluation is difficult because it often requires judg…
GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards
Tej Deep Pala, Vernon Toh, Soujanya Poria
Reinforcement learning with verifiable rewards (e.g. GRPO) is now a common way to improve mathematical reasoning in Large Language Models (LLMs). However, current methods usually b…
Chain-of-Glimpse: Search-Guided Progressive Object-Grounded Reasoning for Video Understanding
Zhixuan Wu, Quanxing Zha, Teng Wang +6
Video understanding requires identifying and reasoning over semantically discriminative visual objects across frames, yet existing object-agnostic solutions struggle to effectively…
Beyond What to Select: A Plug-and-play Oscillatory Data-Volume Scheduling for Efficient Model Training
Suorong Yang, Hanqi Zhu, Hai Gan +4
Data selection accelerates training by identifying representative training data while preserving model performance. However, existing methods mainly focus on designing sample-impor…
-mem: Efficient Online Memory for Large Language Models
Jingdi Lei, Di Zhang, Junxian Li +7
Large language models increasingly need to accumulate and reuse historical information in long-term assistants and agent systems. Simply expanding the context window is costly and…
Post-Reasoning: Improving the Performance of Non-Thinking Models at No Cost
Richmond Sin Jing Xuan, Rishabh Bhardwaj, Soujanya Poria
As the widespread adoption of Large Language Models (LLMs) accelerates, token consumption from intermediate reasoning traces increasingly contributes to inference latency and opera…
Stacked from One: Multi-Scale Self-Injection for Context Window Extension
Wei Han, Pan Zhou, Soujanya Poria +1
The limited context window of contemporary large language models (LLMs) remains a primary bottleneck for their broader application across diverse domains. Although continual pre-tr…
Data Agent: Learning to Select Data via End-to-End Dynamic Optimization
Suorong Yang, Fangjian Su, Hai Gan +5
Dynamic Data selection aims to accelerate training by prioritizing informative samples during online training. However, existing methods typically rely on task-specific handcrafted…
From Perception to Action: An Interactive Benchmark for Vision Reasoning
Yuhao Wu, Maojia Song, Yihuai Lan +8
Understanding the physical structure is essential for real-world applications such as embodied agents, interactive design, and long-horizon manipulation. Yet, prevailing Vision-Lan…
Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems
Ruiwen Zhou, Maojia Song, Xiaobao Wu +8
Individual agents in multi-agent (MA) systems often lack robustness, tending to blindly conform to misleading peers. We show this weakness stems from both sycophancy and inadequate…
Exact Flow Linear Attention: Exact Solution from Continuous-Time Dynamics
Jingdi Lei, Di Zhang, Soujanya Poria
In this paper, we introduce Exact Flow Linear Attention~(EFLA), an exact-flow formulation of delta-rule linear attention. We show that the delta-rule update can be interpreted as a…
NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards
Chia-Yu Hung, Navonil Majumder, Haoyuan Deng +7
Vision--language--action (VLA) models have recently shown promising performance on a variety of embodied tasks, yet they still fall short in reliability and generalization, especia…
10 Open Challenges Steering the Future of Vision-Language-Action Models
Soujanya Poria, Navonil Majumder, Chia-Yu Hung +7
Due to their ability of follow natural language instructions, vision-language-action (VLA) models are increasingly prevalent in the embodied AI arena, following the widespread succ…
Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned
Brandon Ong, Tej Deep Pala, Vernon Toh +2
Process Reward Models (PRMs) provide step-level supervision that improves the reliability of reasoning in large language models. While PRMs have been extensively studied in text-ba…