Why Convolution Still Matters: Evaluating Inductive Biases in Cryospheric Image Classification
Research
Research News
New papers, breakthroughs and academic AI research
Ideological Stance Detection in a Low-Resource Language: Polarization in Bangladeshi Public vs Private University Discourse on Social Media
Research
Understanding and Mitigating Hallucination Escape in Tool-Using LLM Agents
Research
DUET: Co-Evolving Solver and Grader Agents
Research
MemLeak: Cross-User Semantic Leakage in Multi-Tenant AI Agent Memory
Research
From Latent Space to Jacobian Space: Measuring, Evading, and Training Against Safety-Content Accessibility
Research
GlitchPatch: Repairing Glitch Tokens in Frozen Language Models via Local Retokenization
Research
Slaying the Hydra: Interaction-Aware Circuit Discovery in Language Models
Research
ALoDLM: Adaptively Looped Diffusion Language Models
Research
Language-Conditioned Token and Reasoning Efficiency in Large Language Models: A Paired Cross-Lingual Study Protocol
Research
XTurnix: Large-Scale Self-Supervised Turn Control through Two-State Binary Decisions
Research
Scaling 3D Visual Grounding in Abdominal CT
Research