TrajLong: Co-Designing Agentic and Long-Context Supervision for Mid-Training
Research
Research News
New papers, breakthroughs and academic AI research
EgoExo-Next:Benchmarking Vision-Language Models on Visual-Option Next-State and Cross-View Reasoning
Research
FASTER: Fast Adjoint Stochastic Transport for Endpoint Refinement in Reward-Guided Image Editing
Research
EagleDepth: Efficient Fine-Grained Depth Estimation via Pixel Diffusion Decoder
Research
What to Preserve in Recursive Computation: A Local Predictive Sufficiency Principle
Research
Strong Helps Weak: Directional Cross-Modal Alignment Transfer in Multi-modal LLMs
Research
Efficient Neural Surrogates for Linear Radiation Transport on the Lattice and Hohlraum benchmarks
Research
RPFQ-ViT: Rotated Phase-Frame Quantization for Extremely Low-Bit Weights in Vision Transformers
Research
When LLMs Sit Above Diagnostic Tools: Unrealized Complementarity in Industrial Fault Diagnosis
Research
Homogeneous Semantic Alignment and Hierarchical Expert Routing for Radiology Report Generation
Research
Self-Generated Feedback Destabilizes Test-Time Training: A Causal Decomposition of Long-Horizon Adaptation
Research
Integrated Imputation-Classification for Supervised Learning with Missing Data
Research