What's wrong with that though? BTC handles forks just fine. Eventually one fork will win out and life will continue on as usual.
The bigger issue this paper presents is that miners become incentivized to mine empty blocks. But can't you just enforce a minimum transaction count on blocks?
There's only incentive to do that if the mempool is empty. If the mempool is full, there will be plenty of transactions for both the first miner and the next miner.
Wait... This entire paper only makes sense if the mempool is near empty. If the mempool is full, then there is no reason to mine an empty/partial block because there will always be transactions left for future miners.
So basically: