12 papers
On-Policy Residual Learning for Diffusion Language Models
Yifan Yu, Yuqing Jian, Jisen Li +9
Residual context is key to unlocking the speed-quality Pareto frontier of diffusion language models (DLMs) by carrying forward predictive distributions across denoising steps. Yet…
Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation
Zhongzhu Zhou, Qingyang Wu, Junxiong Wang +4
Hybrid linear attention models offer an appealing path to faster long-context inference: they reduce the quadratic cost and KV-cache burden of full softmax attention while retainin…
Introspective Diffusion Language Models
Yifan Yu, Yuqing Jian, Junxiong Wang +12
Diffusion language models promise parallel generation, yet still lag behind autoregressive (AR) models in quality. We stem this gap to a failure of introspective consistency: AR mo…
Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution
Monishwaran Maheswaran, Leon Lakhani, Zhongzhu Zhou +16
We show that verifier-free evolution is bottlenecked by both diversity and efficiency: without external correction, repeated evolution accelerates collapse toward narrow modes, whi…
CARE: Covariance-Aware and Rank-Enhanced Decomposition for Enabling Multi-Head Latent Attention
Zhongzhu Zhou, Fengxiang Bie, Ziyan Chen +6
Converting pretrained attention modules such as grouped-query attention (GQA) into multi-head latent attention (MLA) can improve expressivity without increasing KV-cache cost, maki…
: Unifying Generation and Self-Verification for Parallel Reasoners
Harman Singh, Xiuyu Li, Kusha Sareen +14
Test-time scaling for complex reasoning tasks shows that leveraging inference-time compute, by methods such as independently sampling and aggregating multiple solutions, results in…
ThunderAgent: A Simple, Fast and Program-Aware Agentic Inference System
Hao Kang, Ziyang Li, Weili Xu +7
Large language models(LLMs) are now used to power complex multi-turn agentic workflows. Existing systems run agentic inference by loosely assembling isolated components: an LLM inf…
When RL Meets Adaptive Speculative Training: A Unified Training-Serving System
Junxiong Wang, Fengxiang Bie, Jisen Li +14
Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentangle speculator training from serving, treating speculator training as a standalone…
Distilling Token-Trained Models into Byte-Level Models
Zishuo Bao, Jiaqi Leng, Junxiong Wang +2
Byte Language Models (BLMs) have emerged as a promising direction for scaling language models beyond tokenization. However, existing BLMs typically require training from scratch on…
Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost
Haojun Xia, Xiaoxia Wu, Jisen Li +12
The KV cache is a dominant memory bottleneck for LLM inference. While 4-bit KV quantization preserves accuracy, 2-bit often degrades it, especially on long-context reasoning. We cl…
Beat the long tail: Distribution-Aware Speculative Decoding for RL Training
Zelei Shao, Vikranth Srivatsa, Sanjana Srivastava +12
Reinforcement learning(RL) post-training has become essential for aligning large language models (LLMs), yet its efficiency is increasingly constrained by the rollout phase, where…
Opportunistic Expert Activation: Batch-Aware Expert Routing for Faster Decode Without Retraining
Costin-Andrei Oncescu, Qingyang Wu, Wai Tong Chung +5
An increasing number of LLMs employ Mixture-of-Experts (MoE) architectures where the feed-forward layer is replaced by a pool of experts and each token only activates a small subse…