Tong Zhang

Achieving 95% recognition accuracy in human activity recognition with just 16 unlabeled samples highlights a breakthrough in sim-to-real transfer learning for wireless sensing.

Models can identify abstract structures in isolation but fail dramatically when asked to translate that understanding across different contexts, revealing a critical gap in AI's reasoning abilities.

Joint pretraining on Ego2Robot-synthesized data boosts robot generalization, achieving unprecedented scale and diversity in training datasets.

Agents can now make more accurate decisions by effectively compressing multimodal memory, closing the gap with human performance in complex environments.

LGFNet achieves significant accuracy improvements in sleep staging, particularly in challenging transition segments, outperforming existing methods by notable margins.

AsyncWebRL achieves a staggering 2.9× increase in training throughput while setting a new state-of-the-art performance for web agents on challenging tasks.

Fewer than two edits can enable 76.2% of unsafe images to bypass safety classifiers while retaining their malicious intent, exposing critical vulnerabilities in current moderation systems.

Verified workflows in Lean4Agent outperform unverified ones by nearly 12%, showcasing the power of formal methods in enhancing LLM agent reliability.

OpenWebRL-4B sets a new benchmark for open-source visual web agents, achieving impressive success rates with minimal initial data while outperforming larger-scale competitors.

FLAME uncovers a hidden statistical energy gap in AI-generated images, enabling precise localization of forgeries that traditional methods miss.

One model to control them all: Qwen-VLA achieves impressive zero-shot generalization across diverse robotic tasks and embodiments by unifying vision-language-action modeling.

Stop hand-crafting pseudo-labels: this framework learns to generate and select them for semi-supervised segmentation, boosting performance on RefCOCO, RefCOCO+, and RefCOCOg.

Forget patch-based image tokenization: channel-wise quantization unlocks better codebook utilization and text-to-image generation by representing images as discrete levels of visual detail.

Looping language models isn't just for single agents anymore: Recursive Multi-Agent Systems (RecursiveMAS) show that agent collaboration itself can be scaled through recursion, yielding faster and more efficient problem-solving.

Achieve state-of-the-art low-light image enhancement with real-time inference using an extremely lightweight and unsupervised framework.

GUI agents can achieve significantly stronger task-solving capabilities through carefully designed post-training and data curation, without relying on costly online data collection.