#ifndef LOCAL
#define FAST_IO
#endif

#define INT128

// ============
#include <bits/stdc++.h>
#define OVERRIDE(a, b, c, d, ...) d
#define REP2(i, n) for (i32 i = 0; i < (i32)(n); ++i)
#define REP3(i, m, n) for (i32 i = (i32)(m); i < (i32)(n); ++i)
#define REP(...) OVERRIDE(__VA_ARGS__, REP3, REP2)(__VA_ARGS__)
#define PER2(i, n) for (i32 i = (i32)(n)-1; i >= 0; --i)
#define PER3(i, m, n) for (i32 i = (i32)(n)-1; i >= (i32)(m); --i)
#define PER(...) OVERRIDE(__VA_ARGS__, PER3, PER2)(__VA_ARGS__)
#define ALL(x) begin(x), end(x)
#define LEN(x) (i32)(x.size())
using namespace std;
using u32 = unsigned int;
using u64 = unsigned long long;
using i32 = signed int;
using i64 = signed long long;
using f64 = double;
using f80 = long double;
using pi = pair<i32, i32>;
using pl = pair<i64, i64>;
template <typename T>
using V = vector<T>;
template <typename T>
using VV = V<V<T>>;
template <typename T>
using VVV = V<V<V<T>>>;
template <typename T>
using VVVV = V<V<V<V<T>>>>;
template <typename T>
using PQR = priority_queue<T, V<T>, greater<T>>;
template <typename T>
bool chmin(T &x, const T &y) {
    if (x > y) {
        x = y;
        return true;
    }
    return false;
}
template <typename T>
bool chmax(T &x, const T &y) {
    if (x < y) {
        x = y;
        return true;
    }
    return false;
}
template <typename T>
i32 lob(const V<T> &arr, const T &v) {
    return (i32)(lower_bound(ALL(arr), v) - arr.begin());
}
template <typename T>
i32 upb(const V<T> &arr, const T &v) {
    return (i32)(upper_bound(ALL(arr), v) - arr.begin());
}
template <typename T>
V<i32> argsort(const V<T> &arr) {
    V<i32> ret(arr.size());
    iota(ALL(ret), 0);
    sort(ALL(ret), [&](i32 i, i32 j) -> bool {
        if (arr[i] == arr[j]) {
            return i < j;
        } else {
            return arr[i] < arr[j];
        }
    });
    return ret;
}
#ifdef INT128
using u128 = __uint128_t;
using i128 = __int128_t;
#endif
[[maybe_unused]] constexpr i32 INF = 1000000100;
[[maybe_unused]] constexpr i64 INF64 = 3000000000000000100;
struct SetUpIO {
    SetUpIO() {
#ifdef FAST_IO
        ios::sync_with_stdio(false);
        cin.tie(nullptr);
#endif
        cout << fixed << setprecision(15);
    }
} set_up_io;
void scan(char &x) { cin >> x; }
void scan(u32 &x) { cin >> x; }
void scan(u64 &x) { cin >> x; }
void scan(i32 &x) { cin >> x; }
void scan(i64 &x) { cin >> x; }
void scan(f64 &x) { cin >> x; }
void scan(string &x) { cin >> x; }
template <typename T>
void scan(V<T> &x) {
    for (T &ele : x) {
        scan(ele);
    }
}
void read() {}
template <typename Head, typename... Tail>
void read(Head &head, Tail &...tail) {
    scan(head);
    read(tail...);
}
#define CHAR(...)     \
    char __VA_ARGS__; \
    read(__VA_ARGS__);
#define U32(...)     \
    u32 __VA_ARGS__; \
    read(__VA_ARGS__);
#define U64(...)     \
    u64 __VA_ARGS__; \
    read(__VA_ARGS__);
#define I32(...)     \
    i32 __VA_ARGS__; \
    read(__VA_ARGS__);
#define I64(...)     \
    i64 __VA_ARGS__; \
    read(__VA_ARGS__);
#define F64(...)     \
    f64 __VA_ARGS__; \
    read(__VA_ARGS__);
#define STR(...)        \
    string __VA_ARGS__; \
    read(__VA_ARGS__);
#define VEC(type, name, size) \
    V<type> name(size);       \
    read(name);
#define VVEC(type, name, size1, size2)    \
    VV<type> name(size1, V<type>(size2)); \
    read(name);
// ============

#ifdef DEBUGF
#else
#define DBG(...) (void)0
#endif

// [0, 1, ..., 2^d], make k
V<i32> slv(i32 d, i32 k) {
    i32 mask = (1 << d) - 1;
    i32 low = (k & mask) ^ mask;
    V<i32> p((1 << d) + 1);
    REP(i, 1 << d) {
        p[i] = i ^ low;
    }
    p[1 << d] = 1 << d;
    if (!((k >> d) & 1)) {
        swap(p[0], p[1 << d]);
    }
    return p;
}

V<i32> solve(i32 n, i32 k) {
    V<i32> ds;
    REP(d, 31) {
        if ((n >> d) & 1) {
            ds.push_back(d);
        }
    }
    i32 mx = (1 << ds.back());
    if (LEN(ds) > 1) {
        mx <<= 1;
    }
    if (k >= mx) {
        return V<i32>();
    }
    V<i32> cur;
    for (i32 d : ds) {
        i32 top = ((n >> d) - 1) << d;
        i32 mask = (1 << d) - 1;
        i32 low = ~k & mask;
        DBG(d, top, low);
        V<i32> p(1 << d);
        REP(i, 1 << d) {
            p[i] = top + (i ^ low);
        }
        for (i32 elem : cur) {
            p.push_back(elem);
        }
        if (!((k >> d) & 1)) {
            REP(i, LEN(cur)) {
                swap(p[i], p[(1 << d) + i]);
            }
        }
        cur.swap(p);
        DBG(cur);
    }
    return cur;
}

void ts(i32 n, i32 k) {
    V<i32> p = solve(n, k);
    if (p.empty()) {
        cout << "No\n";
        return;
    }
    cout << "Yes\n";
    REP(i, n) {
        cout << i << " \n"[i + 1 == n];
    }
    REP(i, n) {
        cout << p[i] << " \n"[i + 1 == n];
    }
    i32 t = 0;
    REP(i, n) {
        t |= i & p[i];
    }
    DBG(n, k);
    assert(t == k);
}

void solve() {
    if (0) {
        REP(n, 1, 10) {
            REP(k, 10) {
                ts(n, k);
            }
        }
    }
    I32(n, k);
    ts(n, k);
}

int main() {
    i32 t = 1;
    // cin >> t;
    while (t--) {
        solve();
    }
}