Foresight: planning future perception in streaming VLMs without retraining
Research
Research News
New papers, breakthroughs and academic AI research
Writerslogic at PAN 2026: Process over Content for Robust Detection under Domain Shift
Research
Harnessing LLMs as Agents: What Does It Cost?
Research
Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It
Research
Post-Training Quantization of Autoregressive Weather Models
Research
Bounded Reachability & Jailbreak Detection via Contraction-Constrained State Space Models
Research
When to Compile a Computer-Use Agent? Measuring Payback and Making Compilation Decisions for Token Efficiency
Research
Reliable Self-Evolution with Imperfect Proxy Rewards
Research
A Benchmark for Spatially Grounded Gesture Generation
Research
Harness-Aware Distillation for Small Language Model Agents
Research
Token Space: A Category Theory Framework for AI Computations
Research
Can SGD Handle Heavy-Tailed Noise?
Research