AgentTell: Behavioural Side-Channel Leakage in Browser-Use Agents
Paper • 2609.32915 • Published • 3
liandun110
liandun110
AI & ML interests
None yet
Recent Activity
upvoted a paper about 5 hours ago
AgentTell: Behavioural Side-Channel Leakage in Browser-Use Agents upvoted a paper about 5 hours ago
Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation upvoted a paper about 5 hours ago
SEAD: A State-Based Perspective on Attack and Defense in Tool-Using AgentsOrganizations
None yet
upvoted 20
papers about 5 hours ago
Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation
Paper • 2609.38172 • Published • 1
SEAD: A State-Based Perspective on Attack and Defense in Tool-Using Agents
Paper • 2609.34518 • Published • 4
PlaylistEval: Can Video-Language Judges Be Trusted at Day Scale and Beyond?
Paper • 2609.34314 • Published • 5
One Proposal for Every Margin: Zero-Shot Amortized Sequential Importance Sampling for Binary Matrices
Paper • 2609.35514 • Published • 5
Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusion
Paper • 2609.36014 • Published • 6
AnyStep-WAM: Budget-Aligned Distillation and Adaptive Inference for World Action Models
Paper • 2609.33748 • Published • 5
Hyperspherical Semantic Trajectory Analysis: Mapping Technological Diffusion across Academic Preprints, Patent Signals, and Compute Scaling
Paper • 2609.35845 • Published • 5
Principled Thoughts for Latent Recursive LLM Systems
Paper • 2609.36159 • Published • 6
PrismQuant: Optimal Null-Space Rotations for Grouped Quantizers
Paper • 2609.32429 • Published • 7
CaptchaArena: A Large-Scale, Fine-Grained Dataset for Training Computer-Use Agents on Interactive CAPTCHAs
Paper • 2609.31957 • Published • 6
Understanding On-Policy Distillation: A Mechanistic Interpretability Perspective via Sparse Crosscoders
Paper • 2609.35210 • Published • 7
Pretraining Transformers with Quantized Softmax in Attention
Paper • 2609.33591 • Published • 7
StructRL: Online Structured Reinforcement Learning for Long-Horizon Vision-Language-Action Tasks
Paper • 2609.36352 • Published • 6
Scaffolding Minds: Optimizing Latent Visual Target Representations for Multimodal Reasoning
Paper • 2608.19669 • Published • 6
Improved Distributional Diffusion Models
Paper • 2609.37147 • Published • 6
Real2Gym: Building Gyms from Videos, Bringing Skills to Robots
Paper • 2609.37089 • Published • 7
WISE-ATTA: When to Ask for Labels in Budgeted Active Test-Time Adaptation
Paper • 2609.37687 • Published • 7
Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE
Paper • 2609.38140 • Published • 7
Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement
Paper • 2609.34528 • Published • 7