Search papers, labs, and topics across Lattice.
Beijing University of Posts and Telecommunications
8
0
10
OmniLLMs can now confess which specific evidence tokens rely on, enabling targeted hallucination correction without retraining.
Proposals that consider user evaluability can dramatically enhance AI assistant performance, revealing that what users accept and what they need to learn can diverge significantly.
Silent divergence in dialogue can be effectively addressed by modeling Theory-of-Mind, leading to substantial gains in understanding and intervention quality.
Misunderstandings in dialogue arise not from a lack of information but from the critical importance of perspective in grounding references.
Explicitly incorporating multimodal belief representations into planning leads to significantly more robust navigation in uncertain environments.
GUI-AC transforms how GUI agents learn by stabilizing their performance amidst the chaos of non-stationary environments.
A small fraction of sharp dimensions governs the generalization of PEFT methods, and optimizing these can lead to substantial performance gains.
