Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
eARCO: Efficient Automated Root Cause Analysis with Prompt OptimizationMicrosoft · IEEE/ACM International Conference on Automated Software Engineering (ASE)1 citationOct 7AbridgeKV: Compressing Long Reasoning into the KV Cache of Learned Pause TokensMicrosoft · arXiv (Cornell University)Oct 7Safe at One Loop, Risky at Another: Aligning Safety Across Recurrent Depths in Looped Language ModelsMicrosoft · arXiv (Cornell University)Oct 7The Missing Fourth Term for the Emulation Tensor Memory Equilibrium (TME) Model: The Residue Deconstruction CostNVIDIA · arXiv (Cornell University)Oct 7Code Understanding is a Bottleneck for Coding AgentsMicrosoft · arXiv (Cornell University)Oct 7Conversational Voice Aesthetic Model with Reinforcement Learning from Human ListenersMeta · arXiv (Cornell University)Oct 7RollVerify: Bridging Efficiency and Accuracy in Long-Tail Rollout Reinforcement LearningSenseTime · arXiv (Cornell University)Oct 7VideoEvolve: Co-Evolving Memory and Retrieval for Long Video UnderstandingAlibaba · arXiv (Cornell University)Oct 7Self-correction Optimization for Interleaved Multimodal GenerationSenseTime · 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 7Ream: Unfolding Mutual Awareness in Human-Agent WorkspacesAllen Institute for AI · arXiv (Cornell University)Oct 7ActionNex: A Production-Grade System for Next-Best-Action Recommendation in Cloud Outage ManagementMicrosoft · IEEE/ACM International Conference on Automated Software Engineering (ASE)Oct 7Dual-QK: Sharp Queries and Flat Keys for Prunable 2-bit KV CachesAlphabet · arXiv (Cornell University)Oct 7Symmetric Submodular Minimization from ComparisonsAlphabet · arXiv (Cornell University)Oct 7TaoD2C-Bench: Benchmarking MLLMs for Industrial UI Code Generation Beyond Visual FidelityAlibaba · arXiv (Cornell University)Oct 7Let the Library Speak: Self-Advertised Method Selection for Formal ProvingAlphabet · arXiv (Cornell University)Oct 7Catching Developers in the Flow: Low-Latency Agentic Program Repair at Google ScaleAlphabet · IEEE/ACM International Conference on Automated Software Engineering (ASE)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 7CtxFuzz: Context-Aware Directed Fuzzing via Runtime Fuzzer-Agent CooperationMicrosoft · IEEE/ACM International Conference on Automated Software Engineering (ASE)Oct 7RECAST: Learning to Compute the Right Context through Adaptive Evidence RoutingAlphabet · arXiv (Cornell University)Oct 7Pareto-optimal quantum kernel selection for unsupervised anomaly detection on real malware beaconing dataMultiverse Computing · arXiv (Cornell University)Oct 7Characterizing the role of reasoning tokens in large language models as state over tokensAllen Institute for AI · Nature Machine IntelligenceOct 7ECLAIR: A Causally-Grounded AI Framework for Scientific Discovery in Empirical Software EngineeringMicrosoft · 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 7