GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation
Paper • 2609.05588 • Published • 49
AI & ML interests
Natural Language Processing
Recent Activity
View all activity
Papers
MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents
ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step
soujanyaporia
authored 20
papers about 8 hours ago
MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents
Paper • 2608.31022 • Published • 9
ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step
Paper • 2608.02358 • Published • 11
Data Agent: Learning to Select Data via End-to-End Dynamic Optimization
Paper • 2603.07433 • Published
$Σ$-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems
Paper • 2607.27958 • Published • 17
IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation
Paper • 2607.22375 • Published • 9
On the Limits of LLM-as-Judge for Scientific Novelty Assessment
Paper • 2606.12071 • Published • 3
GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards
Paper • 2606.04889 • Published • 4
Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost
Paper • 2605.06165 • Published • 1
$δ$-mem: Efficient Online Memory for Large Language Models
Paper • 2605.12357 • Published • 133
DialogXpert: Driving Intelligent and Emotion-Aware Conversations through Online Value-Based Reinforcement Learning with LLM Priors
Paper • 2505.17795 • Published
Stacked from One: Multi-Scale Self-Injection for Context Window Extension
Paper • 2603.04759 • Published
Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems
Paper • 2601.21742 • Published
From Perception to Action: An Interactive Benchmark for Vision Reasoning
Paper • 2602.21015 • Published • 26
Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysis
Paper • 2107.13669 • Published
Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics
Paper • 2512.12602 • Published • 44
NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards
Paper • 2511.14659 • Published • 13
10 Open Challenges Steering the Future of Vision-Language-Action Models
Paper • 2511.05936 • Published • 6
Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics
Paper • 2510.05137 • Published • 6
OffTopicEval: When Large Language Models Enter the Wrong Chat, Almost Always!
Paper • 2509.26495 • Published • 13