TerraVis: Towards Evaluation of World-Grounded Visual Consistency in Text-to-Image Generation via MLLM Workflows
Research
Research News
New papers, breakthroughs and academic AI research
iS-KV: Online Low-Rank KV Cache Compression via Block-Incremental SVD
Research
Trained Agentic Context Management
Research
AMBER: Multi-View Adaptive Budget Allocation for Listwise Vision-Language Reranking
Research
Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards
Research
BitNest: Bit-Nested Speculative Decoding for Memory-Efficient LLM Inference Acceleration
Research
Inherit-MAS: Test-Time Evolution of Multi-Agent Systems through Workflow and Execution Inheritance
Research
Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite
Research
Efficient Neural Field Learning via Adaptive Coverage and Focused Sampling
Research
FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training
Research
Validated Data Onboarding for AI Demand Forecasting on U.S. Building Meter Data: Design, Controlled Evaluation, and a Corrected Negative Result
Research
MLCommons Jailbreak Benchmark v1.0
Research