NEURIPS / EMNLP / LOG
2026
Learn
NeurIPS
SCOPE

Self-play for open-ended tasks

EMNLP
Composing steering vectors

Controlling behaviours without interference

LoG
Graph-to-table interfaces

What controls relational generalisation?

Inspect
NeurIPS
LOCOS

What retrieval heads actually write

EMNLP
Multimodal retrieval heads

Can retrieval heads see images?

Evaluate
NeurIPS
Composed image retrieval

When benchmarks admit shortcuts

NeurIPS
AI psychophysics

Grounding behavioural evaluation

EMNLP
Hidden VLM instability

Same answer, different representations

PREPRINTS
SPSD / FACE-Eval / VLM frequency filtering