1 citations · 2 across the 13 of their papers we have counts for
13 papers
WALL-SS: Scaling Long-horizon World Models via Next-Scale Autoregression
Maeve Zhang, Rain Sun, Xiang Wang +22
Generative world models provide robots with predictive models of how the world evolves under interaction, with growing potential for simulation, planning, policy evaluation, and ro…
SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment
Hao Li, Jingkun An, Zijun Song +8
Aligning Large Language Models (LLMs) with human values often degrades their general capabilities, termed the alignment tax. Existing methods mitigate this by balancing dual object…
WALL-WM: Carving World Action Modeling at the Event Joints
Shalfun Li, Victor Yao, Charles Yang +29
WALL-WM is a World Action Model that shifts video-action learning from chunk-centric optimization to event-grounded Vision-Language-Action pretraining, using semantically coherent…
Shortcut to Nowhere: Demystifying Deep Spurious Regression
Guanrong Xu, Jessica Li, Hao Wang +1
Real-world regression often exhibits shortcuts: attributes that are spuriously correlated with continuous targets in training, yet unreliable under deployment shifts; regressing ta…
Wall-OSS-0.5 Technical Report
Ryan Yu, Pushi Zhang, Starrick Liu +24
Large-scale Vision-Language-Action (VLA) pretraining is increasingly adopted as the foundation for robot policies, yet the evidence for pretrained VLAs is almost invariably reporte…
Representation Collapse in Sequential Post-Training of Large Language Models
Yichen Liu, Mingyu Chen, Hao Wang +7
Large language models are now adapted through chains of post-training stages rather than through a single instruction-tuning pass. This paper studies whether such sequential post-t…
FedSDR: Federated Self-Distillation with Rectification
Ziheng Ren, Zhanming Shen, Hao Wang +2
Federated fine-tuning of Large Language Models faces severe statistical heterogeneity. However, existing model-level defenses often overlook the root cause: intrinsic data distribu…
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…
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…
Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering
Gerasimos Chatzoudis, Zhuowei Li, Gemma E. Moran +2
Sparse Autoencoders (SAEs) are increasingly used to interpret foundation models, but their role as an actionable intervention space remains less understood, especially in vision. W…
The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering
Zhuowei Li, Haizhou Shi, Yunhe Gao +7
Large Vision-Language Models (LVLMs) can reason effectively over both textual and visual inputs, but they tend to hallucinate syntactically coherent yet visually ungrounded content…
Spectrum-Aware Parameter Efficient Fine-Tuning for Diffusion Models
Xinxi Zhang, Song Wen, Ligong Han +6
Adapting large-scale pre-trained generative models in a parameter-efficient manner is gaining traction. Traditional methods like low rank adaptation achieve parameter efficiency by…
Implicit In-context Learning
Zhuowei Li, Zihao Xu, Ligong Han +5
In-context Learning (ICL) empowers large language models (LLMs) to swiftly adapt to unseen tasks at inference-time by prefixing a few demonstration examples before queries. Despite…