Inference & Efficiency
A
Showing 61–90 of 127
-
Unlocking Any-Order Generation in Pretrained Autoregressive Image Models
-
XLaw-JP-27B: A Lightweight Open Model Specialized for Japanese Law
-
Analyzing Condensation on Patterned Surfaces via Deep Learning
-
From Local Recovery to Unified Generation: Discovering Triple Set in Knowledge Graphs via Observation-Anchored Latent Diffusion
-
PhysicsNeMo-Mesh: GPU-Native Meshes and Simulation Cases for Physics AI
-
Build a Financial Research Assistant with Cohere AI on AWSCohere shows how to build a financial research assistant on AWSCohere details a financial research assistant on AWS that combines Embed, Rerank and Parse with SageMaker AI, OpenSearch Serverless and Bedrock to search filings and answer with page-level citations, tuning retrieval quality, latency and cost.
-
Reinforcement Learning for the Game of Balatro: A Fast Simulator and Two-Policy Training Approach
-
Distilling the Shape of Uncertainty: What On-Policy Distillation Learns and How to Predict It
-
Blind Spots: Where Small Language Models Fall Behind Frontier Models on Terminal Tasks
-
Efficient Agentic Audio-Visual Question Answering through Toolset Pruning and Modality Consolidation
-
Leaving, Staying, or Living There? Duration Commonsense Reasoning with Human-LLM Co-annotations
-
SatOps-Decision: Low-Latency Discriminative Decisions for Onboard Satellite Communication Operations
-
Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models
-
Information-Theoretic Reliability--Safety Bounds and Finite-Alignment Dynamics in AI Knowledge Distillation
-
On-Policy Self-Distillation with Teacher Evolution
-
Curriculum-Based Deep Reinforcement Learning for Robust Autonomous Rocket Landing under Atmospheric Uncertainty
-
Co-Evolving Policy and Rubric via Capability Awareness for Open-Ended Generation
-
Persona Learning from Feedback for Personalized AI Assistants
-
Implicit Minor Detection from Multi-Turn Dialogue in High-Risk AI Interactions: A Constrained Self-Evolving LLM Harness
-
AtomSteer: Test-Time Constraint Steering for Atomistic Generative Models
-
SaiVLA-JEPA: Evaluating Future Latent Prediction in JEPA-Conditioned VLA Control
-
DES-JEPA: Learning a Shared Vocabulary for High-Dimensional Discrete Event Sequences
-
DecisionUnlearn-Bench: Unlearning Probabilistic Decisions under Changing Schemas
-
The Code Behind the Layout: AI Agents for Analog Layout Generators
-
Agent Transfer Protocol: Server-Mediated Agent-to-Agent Communication Architecture for the Agentic Web
-
Metacognitive Decoding: Efficient Inference for Diffusion Language Agents
-
GAS-PFN: Graph-Aware Spatiotemporal Prior-Data Fitted Networks for Zero-Shot Traffic Forecasting
-
Zero-Shot Multimodal Event Spotting in Soccer Broadcasts
-
Pneuma: A Large-Scale Real-World Time Series Benchmark for Commercial Aircraft Predictive Maintenance