HMMT
PulseAugur coverage of HMMT — every cluster mentioning HMMT across labs, papers, and developer communities, ranked by signal.
-
KVpop method slashes LLM cache memory use while preserving performance
Researchers have developed KVpop, a novel method for compressing the key-value cache in autoregressive decoding, which is a significant bottleneck for large context windows. KVpop learns an eviction policy by directly s…
-
New framework enables LLMs to share insights during reasoning
Researchers have introduced Collaborative Parallel Thinking (CPT), a novel training-free framework designed to enhance the efficiency of test-time scaling (TTS) for large language models. CPT addresses the issue of redu…
-
MoE models misroute tokens on complex reasoning tasks, study finds
Researchers have identified a significant issue in Mixture-of-Experts (MoE) language models where the routing mechanism, which directs tokens to specific experts, often selects suboptimal paths. While the standard route…