Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs
Research
Research News
New papers, breakthroughs and academic AI research
LLM2Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them
Research
Argo-Bench: Evaluating Data Agents on Enterprise-Scale Workflows
Research
Reward as Observation: Learning Reward-Based Policies for Rapid Adaptation
Research
AutoCompact: Learning When to Compact Context in Long-Horizon Coding Agents
Research
SALD: Self-Referenced Advantage Learning for Diffusion Models
Research
VTR-Bench: A Systematic Benchmark for Evaluating Visual Text Rendering in Video Generation
Research
VoxelSynth3D: Interpretable Volumetric Image-Domain Metal Artifact Reduction with a Paired Synthetic CLINIC-Metal Benchmark
Research
Synthetic training for long-tail haemorrhagic lesion segmentation in data-scarce settings
Research
Reformulation-Contrastive Learning for Mixed Integer Programs
Research
From Knowledge Access to Source Learning: Developing Source-Specific Competence
Research
Hierarchical Continuous Diffusion Language Models
Research