2 citations · 6 across the 8 of their papers we have counts for
8 papers
Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation
Ling Team, Ang Li, Ben Liu +138
We introduce Ling 2.0, a series reasoning-oriented language foundation built upon the principle that every activation boosts reasoning capability. Designed to scale from tens of bi…
Did Models Learn Sufficiently? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation
Yannan Chen, Ruoyu Chen, Wei Wang +6
Current visual models often make predictions based on a limited set of discriminative visual cues. As a result, they may become unreliable when the distribution shifts or when thes…
RECAP: Reproducing Copyrighted Data from LLMs Training with an Agentic Pipeline
André V. Duarte, Xuying li, Bin Zeng +3
If we cannot inspect the training data of a large language model (LLM), how can we ever know what it has seen? We believe the most compelling evidence arises when the model itself…
BTMTrack: Robust RGB-T Tracking via Dual-template Bridging and Temporal-Modal Candidate Elimination
Zhongxuan Zhang, Bi Zeng, Xinyu Ni +1
RGB-T tracking leverages the complementary strengths of RGB and thermal infrared (TIR) modalities to address challenging scenarios such as low illumination and adverse weather. How…
RTrack: Accelerating Convergence for Visual Object Tracking via Pseudo-Boxes Exploration
Guotian Zeng, Bi Zeng, Hong Zhang +2
Single object tracking (SOT) heavily relies on the representation of the target object as a bounding box. However, due to the potential deformation and rotation experienced by the…
LiteTrack: Layer Pruning with Asynchronous Feature Extraction for Lightweight and Efficient Visual Tracking
Qingmao Wei, Bi Zeng, Jianqi Liu +2
The recent advancements in transformer-based visual trackers have led to significant progress, attributed to their strong modeling capabilities. However, as performance improves, r…
Towards Efficient Training with Negative Samples in Visual Tracking
Qingmao Wei, Bi Zeng, Guotian Zeng
Current state-of-the-art (SOTA) methods in visual object tracking often require extensive computational resources and vast amounts of training data, leading to a risk of overfittin…
Efficient Training for Visual Tracking with Deformable Transformer
Qingmao Wei, Guotian Zeng, Bi Zeng
Recent Transformer-based visual tracking models have showcased superior performance. Nevertheless, prior works have been resource-intensive, requiring prolonged GPU training hours…