Rethinking Contrastive Loss in CLIP Post-training: A Complementary Framework with Frozen Text Encoder
Research
Research News
New papers, breakthroughs and academic AI research
Same Outcome, Different Evidence: Intent Recovery in LLM Safety Evaluation
Research
ActiveMedAgent: Cost-Aware Trajectory Learning for Multimodal Medical Diagnosis
Research
When Should Agents Think? Adaptive Reasoning via Cross-Turn Estimation
Research
Is Memorization Context-Sensitive? Prefix-Based Extraction Beyond Isolated Prefixes
Research
Event-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational Agents
Research
Do LLMs Learn from Rewards in Context? : Rethinking the role of reward in In-Context Reinforcement Learning
Research
Adaptive Adversarial Augmentation for Controllable Face Synthesis
Research
RideBench: A Large-Scale Exogenous-Aware Benchmark for Ride-Hailing Time Series Forecasting
Research
FlyMark: Training-Free Invisible Watermarking of 3D Gaussian Splatting via a Fruit Fly Connectome
Research
PIVOT: Perplexity-Informed KD-to-RL Transition Scheduling for Vertical-Domain Few-Shot Distillation
Research
CRISP: Fixing Flying Pixels in Latent LiDAR Generation via Diffusion Decoding
Research