Token-to-Mask remasking improves self-correction in diffusion LLMs by resetting erroneous commitments to masks rather than overwriting them, yielding +13.33 points on AIME 2025 and +8.56 on CMATH.
CMATH: Can your language model pass Chinese elementary school math test?,
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Validity-calibrated reasoning distillation improves transfer of reasoning skills by modulating updates based on relative local validity of next steps instead of enforcing full trajectory imitation.
CAMEL is a scaling law capturing nonlinear model-size and mixture interactions to extrapolate optimal data mixtures for large LLMs from small-model experiments, reducing optimization cost by 50% and improving benchmarks by up to 3%.
LLaDA2.0 scales discrete diffusion language models to 100B parameters via systematic conversion from autoregressive models using a 3-phase WSD training scheme and releases open-source 16B and 100B MoE variants.
OALMs exhibit order-dependent likelihoods up to 0.49 nats/token and a uniform confidence spread maximizes recoverability, motivating Var(log q_t) as a decoding diagnostic.
Dense2MoE unifies pruning of attention modules with upcycling of MLPs into MoE experts to produce on-device LLMs that improve the latency-accuracy Pareto frontier.
AGPO adaptively sets trust-region size and exploration temperature from group reward dispersion, entropy, and KL drift, yielding higher scores than PPO and GRPO on nine math benchmarks under fixed token budget.
MDLMs lag autoregressive models in performance because parallel modeling weakens inter-token dependencies, yet they adapt generation order to task demands and show promise in a generate-then-edit paradigm.
Kimi K2 is a 1-trillion-parameter MoE model that leads open-source non-thinking models on agentic benchmarks including 65.8 on SWE-Bench Verified and 66.1 on Tau2-Bench.
Technical report announcing Ling-2.6 and Ring-2.6 models with hybrid linear attention, evolutionary CoT, and KPop RL for efficient agentic intelligence at scale.
PowLU replaces SwiGLU with a rational-power activation to reduce outlier amplification and numerical instability during large-scale LLM pre-training while matching performance.
An integrated survey organizing AI mathematical reasoning into informal, formal, discovery, and technique axes while cataloging benchmarks and assessing failure modes.
citing papers explorer
No citing papers match the current filters.