Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code RepairAlibaba · arXivOct 8Regression Accumulation in Multi-turn LLM Programming ConversationsAlibaba · IEEE/ACM International Conference on Automated Software Engineering (ASE)1 citationOct 7VideoEvolve: Co-Evolving Memory and Retrieval for Long Video UnderstandingAlibaba · arXiv (Cornell University)Oct 7FlowChecker: One Command to Model Check Control-Flow Rules in Industrial JavaAlibaba · IEEE/ACM International Conference on Automated Software Engineering (ASE)Oct 7TaoD2C-Bench: Benchmarking MLLMs for Industrial UI Code Generation Beyond Visual FidelityAlibaba · arXiv (Cornell University)Oct 7LIFT-SE: Linguistic Inference Followed by Flow Transformation for Generative Speech EnhancementAlibaba · arXiv (Cornell University)Oct 7ABACI: Automated Downstream Bug Resolution via Semantic-Aware Bisection and Convergent BackportingAlibaba · IEEE/ACM International Conference on Automated Software Engineering (ASE)Oct 7Bifrost: Empowering Pretrained Language Model with Fallibility Representation for Log-Based Fault DiagnosisAlibaba · IEEE/ACM International Conference on Automated Software Engineering (ASE)Oct 7TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language ModelsAlibaba · arXiv (Cornell University)Oct 6Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision ReliabilityAlibaba · arXiv (Cornell University)Oct 6MMPostTrainBench: Benchmarking Autonomous Research for Multimodal Post-TrainingAlibaba · arXiv (Cornell University)Oct 4Towards Unbiased On-Policy Distillation for Block Diffusion Language ModelsAlibaba · arXiv (Cornell University)Oct 4OpticalRec: Unified Optical Vision-Language Representation for Multimodal RecommendationAlibaba · arXiv (Cornell University)Oct 4Sibyl: An Efficient Small-large Model Collaboration Framework for Long-horizon TasksAlibaba · arXiv (Cornell University)Oct 4Causal Improvement Graph for Agentic Harness OptimizationAlibaba · arXiv (Cornell University)Oct 4Geometry-Aware Preference Optimization for Text-to-Image Diffusion ModelsAlibaba · arXiv (Cornell University)Oct 4Principles that Guide, Actions that Inform: Agent Evolution via Knowledge AbstractionAlibaba · arXiv (Cornell University)Oct 3Playing social deduction games with reinforcement fine-tuned large language modelsAlibaba · arXiv (Cornell University)Oct 3Decouple, Purify and Unite: Semantic-Structural Prototype Learning for Federated Medical SegmentationAlibaba · arXiv (Cornell University)Oct 3From Probe Scores to Alarm Policies: Operational Validity of Activation Monitors for Language-Model AgentsAlibaba · arXiv (Cornell University)Oct 3The GPU Resilience Lottery: Understanding and Taming Real-World Hardware Errors in Heterogeneous AI InfrastructureAlibaba · ACM Transactions on Architecture and Code OptimizationOct 3HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing AgentsAlibaba · arXiv (Cornell University)Oct 2Training Numerical Intelligence via Auto-Diagnosis and Skill DiscoveryAlibaba · arXiv (Cornell University)Oct 2D2K-Bench: Can LLM Agents Turn Expert Designs into Efficient GPU Kernels?Alibaba · arXiv (Cornell University)Oct 2Learning to Revise Reasoning with Segment-wise On-Policy DistillationAlibaba · arXiv (Cornell University)Oct 2