#include<cstdio>

#include<cstring>

#include<cstdlib>

#include<cctype>

#include<cmath>

#include<iostream>

#include<sstream>

#include<iterator>

#include<algorithm>

#include<string>

#include<vector>

#include<set>

#include<map>

#include<stack>

#include<deque>

#include<queue>

#include<list>

#define lowbit(x) (x & (-x))

const double eps = 1e-8;

inline int dcmp(double a, double b){

    if(fabs(a - b) < eps) return 0;

    return a > b ? 1 : -1;

}

typedef long long LL;

typedef unsigned long long ULL;

const int INT_INF = 0x3f3f3f3f;

const int INT_M_INF = 0x7f7f7f7f;

const LL LL_INF = 0x3f3f3f3f3f3f3f3f;

const LL LL_M_INF = 0x7f7f7f7f7f7f7f7f;

const int dr[] = {0, 0, -1, 1, -1, -1, 1, 1};

const int dc[] = {-1, 1, 0, 0, -1, 1, -1, 1};

const int MOD = 1e9 + 7;

const double pi = acos(-1.0);

const int MAXN = 100000 + 10;

const int MAXT = 10000 + 10;

using namespace std;

int a[MAXN];

int yu[MAXN];

map<int, int> mp;

int main(){

    int n, k, m;

    scanf("%d%d%d", &n, &k, &m);

    for(int i = 0; i < n; ++i){

        scanf("%d", &a[i]);

    }

    for(int i = 0; i < n; ++i){

        yu[i] = a[i] % m;

        ++mp[yu[i]];

    }

    int ma = 0;

    int id = 0;

    for(map<int, int>::iterator it = mp.begin(); it != mp.end(); ++it){

        if((*it).second > ma){

            ma = (*it).second;

            id = (*it).first;

        }

    }

    if(ma < k){

        printf("No\n");

    }

    else{

        printf("Yes\n");

        bool flag = true;

        int t = 0;

        for(int i = 0; i < n; ++i){

            if(yu[i] == id){

                if(flag) flag = false;

                else printf(" ");

                printf("%d", a[i]);

                ++t;

                if(t == k) break;

            }

        }

        printf("\n");

    }

    return 0;

}