A new VLA model called SI uses a four-step chain-of-thought to derive driving intent and applies it via classifier-free guidance to a flow-matching trajectory generator, showing competitive Waymo scores and intent-controllable plans.
Advances in Neural Information Processing Systems , year =
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 8verdicts
UNVERDICTED 8roles
background 1polarities
unclear 1representative citing papers
ProofGrid is a new benchmark for LLM reasoning that uses machine-checkable proofs in minimal formal notation, revealing progress on basic tasks but major gaps in complex combinatorial and synthesis reasoning.
PHREEQC-MCQ-200 benchmark shows simulator access raises aggregate accuracy for tool-augmented agents on aqueous geochemistry tasks but produces non-monotonic gains and output-protocol sensitivity.
PRISM weights target examples by model preference to build an improved direction for influence-based data selection in LLM fine-tuning.
Tool identity is linearly readable and steerable in LLMs via mean activation differences, with 77-100% switch accuracy and error prediction from activation gaps.
Introduces an audit-constrained protocol for targeted LLM reasoning tests using finite component grammar and compares score-based CAPS sampling against uniform sampling under matched budgets, finding no audited-yield improvement.
LLMs fail at extended counting of repeated characters due to finite internal states, with abrupt errors persisting across model scales and inference methods.
A case-driven multi-agent system automates the full pipeline of bad-case detection, annotation, and resolution for e-commerce search relevance using Annotator, Optimizer, and User agents plus supporting components.
citing papers explorer
-
Action Emergence from Streaming Intent
A new VLA model called SI uses a four-step chain-of-thought to derive driving intent and applies it via classifier-free guidance to a flow-matching trajectory generator, showing competitive Waymo scores and intent-controllable plans.