activity
20242026
most citedLAB: Large-Scale Alignment for ChatBots

5 citations · 8 across the 17 of their papers we have counts for

collaborators
Showing cs.LGShow all

13 papers · 1 filter

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…