HMMT
PulseAugur coverage of HMMT — every cluster mentioning HMMT across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
WebAI releases TwIL-8B reasoning model, tops MATH-500 benchmark
WebAI has launched TwIL-8B, an 8.8 billion parameter reasoning model built upon IBM's Granite 4.2 8B. This model excels in mathematics and coding tasks, achieving a score of 98.2 on the MATH-500 benchmark, and is design…
-
New AI self-distillation method improves reasoning and reduces hallucinations
Researchers have developed a new method called Steered-Teacher On-Policy Self-Distillation (ST-OPSD) to improve the reasoning capabilities of AI models. This technique addresses issues like hallucinating references and …
-
New CHIMERA dataset boosts LLM reasoning across scientific domains
Researchers have developed CHIMERA, a synthetic dataset of 9,000 samples designed to enhance the reasoning capabilities of large language models (LLMs) across various scientific domains. This dataset addresses challenge…
-
AI performance claims need external validation, not self-reporting
This article argues that AI performance claims should be evaluated based on external validation rather than self-reported metrics. It emphasizes that true performance is demonstrated when a third party administers tests…
-
AI models' math reasoning affected by token limits, study finds
A new research paper explores the impact of token caps on mathematical reasoning in AI models. The study found that different stopping rules (strict vs. advisory) at a 4k token cap can lead to varying accuracy gains, wi…
-
VIDRAFT's Darwin-180B-RSI model tops 5 leaderboards, achieves perfect scores
VIDRAFT has released its Darwin-180B-RSI model, a 180-billion-parameter reasoning model that has achieved top rankings on five Hugging Face leaderboards. The model notably secured perfect scores on the AIME and HMMT ben…
-
New method improves knowledge transfer in large language models
Researchers have developed a new method called Selective Supervision for Direct-OPD (S^2D-OPD) to improve the efficiency of knowledge transfer in large language models. This technique addresses limitations in the origin…
-
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…