T-DIG lets users steer image diversity with natural-language prompts
It keeps the image generator frozen and adds user-directed diversity to open and closed models without weight access.
Stories per day · 30 days
5 RSS
Relatedreasoning-models2reinforcement-learning2scientific-ideation2text-to-image23d-assets1benchmark1document-grounded1generative-models1grpo1image-generation1llm1llm-policy1msr1sampling1test-time1
9 stories, newest first · one card per story
Stories tagged #diversity
Training Reasoning Models to Generate Diverse Scientific Ideas
An 8B model trained with set-level RL generates more diverse scientific ideas than Claude Opus 4.8 and GPT-6 Astra.
Set-level RL trains an 8B model for diverse scientific ideas
Authors say creative utility exceeded Claude Opus 4.8 and GPT-6 Astra without lowering proof-of-concept executability.
Mine, Sample, Render: Test-Time Diversity Alignment Of Generative Models
MSR improves generative-model diversity by sampling corpus-derived attributes and using the model only as a renderer.
Gacha Decoding: Eliciting Diverse Generations Through Instruction Following
Gacha Decoding uses instruction following and an external RNG to elicit diverse, high-quality language-model generations.
Fewer women than ever in UK's 'old boys' club' cyber industry
Women fell to 16 percent of the UK cybersecurity workforce, the lowest share since 2021.
iADD: Improving Alignment and Diversity in Diffusion Policy Optimization
iADD improves the alignment-diversity tradeoff in diffusion-model post-training using incremental Feynman-Kac updates.
Beyond Top-k Skill Retrieval: Diversity-Aware Skill Routing for LLM Agents
DSR reranks LLM agent skills with Determinantal Point Processes to favor complementary, non-redundant sets, improving multi-skill query coverage.
Keep Your Tech FLAME Alive: Trailblazer Suzanne Wheeler
Akamai's FLAME Trailblazer series profiles Suzanne Wheeler's path into cybersecurity and offers advice for women building security careers.