What Gets Hacked in a Collaborative Reward for LLM Recommenders: The Part That Does Not Depend on the User
1 version
RC
Rui Cai
cs.CLcs.LGcs.AIcs.CVcs.CRcs.IRcs.ROcs.SD
On Valency
published · living versionsPreprints & journals
10 papers in the corpus · 2026Triaging Threats to Specialized Guardrails
0 citations
When Vision Speaks for Sound
0 citations
ModelLens: Finding the Best for Your Task from Myriads of Models
0 citations
Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization
0 citations
Your Agent is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs
0 citations
Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation
0 citations
Summarize Before You Speak with ARACH: A Training-Free Inference-Time Plug-In for Enhancing LLMs via Global Attention Reallocation
0 citations
Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution
0 citations
AriadneMem: Threading the Maze of Lifelong Memory for LLM Agents
0 citations
CARPE: Context-Aware Image Representation Prioritization via Ensemble for Large Vision-Language Models
0 citations
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.