.

Author: faikit

app/(default)/(research)/AutonomousDriving/page.tsx

@@ -43,7 +43,7 @@ export default function Home() {
                         Autonomous Driving
                     </h1>
                     <span className="text-xl">
-                        stands at the intersection of intelligence, world modeling, and safety alignment, enabling vehicles to respond to the surroundings effectively for both comfort and safety. We target the crucial areas of autonomous driving, including whole-scene perception systems, critical data generation, and end-to-end decision-making. Our mission is to establish a comprehensive pipeline by leveraging massive real-world driving data and building efficient world representation for safe and generalizable autonomy.
+                        lies at the intersection of intelligence, world modeling, and safety alignment, enabling vehicles to perceive, reason, and act safely in complex environments. We focus on whole-scene perception, critical data generation, and end-to-end decision-making. Our goal is to build a unified and scalable autonomy pipeline grounded in large-scale real-world driving data and efficient world representations.
                     </span>
                     <span className="text-xl">
                         For a complete list of publications, please see <Link href="/publications" className="underline text-o-blue hover:text-o-light-blue">here</Link>.

app/(default)/(research)/EmbodiedAI/page.tsx

@@ -43,7 +43,7 @@ export default function Home() {
                         Embodied AI
                     </h1>
                     <span className="text-xl">
-                        is the integration of artificial intelligence with the physical world, enabling robots to interact with and learn from the real world. We focus on the most critical areas of embodied AI, including humanoid, robot manipulation, and dexterous hand. Our goal is to explore the scaling law for robots, develop general world models, and unveil the power of reinforcement learning to achieve general-purpose embodied agents.
+                        bridges intelligence and the physical world through real-world perception, action, and learning. Focusing on humanoids, manipulation, and dexterous hands, we aim to uncover robot scaling laws, develop general world models, and unlock reinforcement learning for general-purpose embodied agents.
                     </span>
                     <span className="text-xl">
                         For a complete list of publications, please see <Link href="/publications" className="underline text-o-blue hover:text-o-light-blue">here</Link>.

data/publications.tsx

@@ -167,7 +167,7 @@ export const publications: {
                 link: "https://github.com/OpenDriveLab/SimScale",
             },
         ],
-        description: `🏗️ A scalable simulation pipeline that synthesizes diverse and high-fidelity reactive driving scenarios with pseudo-expert.\n🚀 An effective sim-real co-training strategy that improves robustness and generalization across end-to-end planners.\n🔬 A comprehensive recipe that reveals crucial insights into the underlying scaling properties of sim-real learning systems.`,
+        description: `A scalable sim-real learning framework that synthesizes high-fidelity driving data and cboosts end-to-end planners to achieve robust, generalizable autonomy with principled scaling insights.`,
         keys: ['end_to_end_ad'],
         time: '2025.11.28',
         timeline:['te2e'],