LEAD lets LLMs solve checkers jumping puzzles up to size 13 by using lookahead to recover from irreversible errors on hard steps that break extreme decomposition.
Gsm-infinite: How do your llms behave over infinitely increasing context length and reasoning complexity?
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
A graph-grounded Combined Road Substrate framework generates traceable QA pairs from road maps to improve small VLMs on compositional road reasoning tasks.
Power-law data sampling creates beneficial asymmetry in the loss landscape that lets models acquire high-frequency skill compositions first, enabling more efficient learning of rare long-tail skills than uniform distributions.
A factored causal representation learning method improves robustness of reward models in RLHF by isolating causal factors from biases like length and sycophancy using adversarial gradient reversal.
MiMo-V2-Flash is a 309B/15B MoE model trained on 27T tokens with hybrid attention and multi-teacher on-policy distillation that matches larger models like DeepSeek-V3.2 while enabling 2.6x faster decoding via repurposed MTP layers.
citing papers explorer
-
LEAD: Breaking the No-Recovery Bottleneck in Long-Horizon Reasoning
LEAD lets LLMs solve checkers jumping puzzles up to size 13 by using lookahead to recover from irreversible errors on hard steps that break extreme decomposition.
-
Bridging Structure and Language: Graph-Based Visual Reasoning for Autonomous Road Understanding
A graph-grounded Combined Road Substrate framework generates traceable QA pairs from road maps to improve small VLMs on compositional road reasoning tasks.
-
The Power of Power Law: Asymmetry Enables Compositional Reasoning
Power-law data sampling creates beneficial asymmetry in the loss landscape that lets models acquire high-frequency skill compositions first, enabling more efficient learning of rare long-tail skills than uniform distributions.
-
Factored Causal Representation Learning for Robust Reward Modeling in RLHF
A factored causal representation learning method improves robustness of reward models in RLHF by isolating causal factors from biases like length and sycophancy using adversarial gradient reversal.
-
MiMo-V2-Flash Technical Report
MiMo-V2-Flash is a 309B/15B MoE model trained on 27T tokens with hybrid attention and multi-teacher on-policy distillation that matches larger models like DeepSeek-V3.2 while enabling 2.6x faster decoding via repurposed MTP layers.