Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
PRISM: Recovering Instruction Sets from Language Model ActivationsMicrosoft · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Humans’ ALMANAC: A Human Collaboration Dataset of Action-Level Mental Model ANnotations for Agent CollaborationMicrosoft · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1POLARIS: Guiding Small Models to Write Long StoriesAlphabet, Google DeepMind · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language ModelsAllen Institute for AI, Microsoft, OpenAI · Lecture notes in computer scienceJan 1Reconfiguration-Aware Direct-Connect AI Cluster using Spatial-and-Wavelength-Selective SwitchingNVIDIA · Optical Fiber Communication ConferenceJan 1Technology for AI Interconnect Scale-Up SolutionsMeta · Optical Fiber Communication ConferenceJan 1First Field-Operational GraphRAG Agent for Information Query in Large-Scale Hierarchical Optical NetworksAlibaba · Optical Fiber Communication ConferenceJan 1PCIe-over-Optics with OSFP DR8 LPO and an Optical Circuit Switching Fabric for Composable CPU-GPU Resource PoolingAlibaba · Optical Fiber Communication ConferenceJan 1FBHM: Functional Benchmarking and Steering of VLMs for Hateful Meme DetectionMicrosoft · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1COMPASS: Cognitive MCTS-Guided Process Alignment for Safe Search AgentsAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified ModelsAlibaba · Lecture notes in computer scienceJan 1Defrag: Reducing Resource Fragmentation in Large-Scale Heterogeneous GPU ClustersAlibaba · IEEE Transactions on NetworkingJan 1大規模言語モデルの現在地 ――世界の潮流と日本の動向――Google DeepMind · Denshi Jouhou Tsuushin Gakkai Tsuushin Sosaieti magajin/B-plus/Denshi Jouhou Tsuushin Gakkai Tsuushin Sosaeti magajinJan 1Decoding Strategies for Diffusion-Based ASR: A Systematic Evaluation of Confidence-Based ThresholdingGoogle DeepMind · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Mobile-Aptus: Confidence-Driven Proactive and Robust Interaction in MLLM-Based Mobile-Using AgentsMeta · IEEE Transactions on Audio Speech and Language ProcessingJan 1DEPART: DEcomposing PARiTy across Multilingual LLMsMicrosoft · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1InfoQuant: Shaping Activation Distributions for Low-Bit LLM QuantizationAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1Near-Optimal Bounds for Parameterized Euclidean k-MeansAlphabet · arXiv (Cornell University)Jan 1COSY: Compositional 3DGS Synthesis for Disentangled Human Head EditingNVIDIA · Lecture notes in computer scienceJan 1InnerEye-HS: a disease-agnostic clinical tool for hippocampal segmentationMicrosoft · Brain CommunicationsJan 1A Heterogeneous System-on-Chip with an 83 GFLOp/s, 1.2 TFLOp/s/W Parallel Programmable Accelerator for Real-time On-device Learning in Autonomous Nano-UAVsTechnology Innovation Institute · IEEE Open Journal of the Solid-State Circuits SocietyJan 1A Causal Perspective for Enhancing Jailbreak Attack and DefenseAlibaba · Network and Distributed System Security SymposiumJan 1Eureka: Intelligent Feature Engineering for Enterprise AI Cloud Resource Demand PredictionAlibaba · Lecture notes in computer scienceJan 1Problems of Scaling Large Language Model Inference During Simultaneous Operation of Multiple Autonomous AgentsAlphabet · International Journal of Advanced engineering Management and ScienceJan 1D-Rex: Diffusion Rendering for Relightable Expressive AvatarsNVIDIA · Lecture notes in computer scienceJan 1