5 citations · 11 across the 18 of their papers we have counts for
9 papers · 1 filter
Turbo Harness: Instance-Adaptive Harness Optimization
Tunyu Zhang, Hao Wang, Kai Xu +1
Automating the search for effective harnesses is an important step toward enabling agents to recursively self-improve. Existing harness optimizations typically produce a single glo…
Layer-Parallel Inference Reduces Encrypted Nonlinear Depth in Transformers
Ligong Han, Kai Xu, Hao Wang +3
Fully homomorphic encryption (FHE) enables computation on encrypted data, but practical encrypted Transformer inference is bottlenecked by the sequential composition of many nonlin…
sGPO: Trading Inference FLOPs for Training Efficiency in RLVR
Shivchander Sudalairaj, Kai Xu, Akash Srivastava +1
Standard Reinforcement Learning with Verifiable Rewards (RLVR) training allocates a fixed rollout budget to every query, without regard for what each query's difficulty means for t…
Intrinsic Selection and Particle Resampling for Inference-Time Scaling Beyond Domain Verifiability
Giorgio Giannone, Mustafa Eyceoz, Shabana Baig +5
Inference-Time Scaling (ITS) has largely succeeded in verifiable domains like math and coding, where cheap verification enables scalable output selection. However, extending ITS to…
On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation
Andy Han, Kristina Fujimoto, Avidan Shah +5
Aligned models can misbehave in several ways: they are often sycophantic, fall victim to jailbreaks, or fail to include appropriate safety warnings. Consistency training is a promi…
SNLP: Layer-Parallel Inference via Structured Newton Corrections
Ligong Han, Kai Xu, Hao Wang +1
Autoregressive language models execute Transformer layers sequentially, creating a latency bottleneck that is not removed by conventional tensor or pipeline parallelism. We study w…
GIFT: Bootstrapping Image-to-CAD Program Synthesis via Geometric Feedback
Giorgio Giannone, Anna Clare Doris, Amin Heyrani Nobari +3
Generating executable CAD programs from images requires alignment between visual geometry and symbolic program representations, a capability that current methods fail to learn reli…
S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation
Ligong Han, Hao Wang, Han Gao +2
Block-diffusion language models offer a promising path toward faster-than-autoregressive generation by combining block-wise autoregressive decoding with within-block parallel denoi…
Few-Step Diffusion Language Models via Trajectory Self-Distillation
Tunyu Zhang, Xinxi Zhang, Ligong Han +9
Diffusion large language models (DLLMs) have emerged as powerful generative models with the promise of fast text generation through parallel decoding. However, realizing this poten…