spectacle
spectaclecs
AI & ML interests
Multimodal LLM, Agent
Recent Activity
upvoted a paper 3 days ago
Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening liked a dataset 3 months ago
OpenDataArena/MMFineReason-SFT-123K-Qwen3-VL-235B-Thinking upvoted a paper 3 months ago
Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious CodeOrganizations
