Different Tasks, Different Timesteps: Temporal Task-Aware Quantization for Diffusion Language Models
Paper • 2610.31198 • Published • 15
Joe Mama
JoeMama123123123
AI & ML interests
None yet
Recent Activity
upvoted a paper about 17 hours ago
Different Tasks, Different Timesteps: Temporal Task-Aware Quantization for Diffusion Language Models upvoted a paper about 17 hours ago
EvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement? upvoted a paper about 17 hours ago
HyperDrone: Simulation-to-Reality Transfer at Millions of Frames per SecondOrganizations
None yet
upvoted 4
papers about 17 hours ago
EvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement?
Paper • 2610.04184 • Published • 2
HyperDrone: Simulation-to-Reality Transfer at Millions of Frames per Second
Paper • 2610.28950 • Published • 2
Diffusion Language Models Change Speed Across Tasks and Languages
Paper • 2610.25835 • Published • 3
upvoted 16
papers 1 day ago
Who Takes the Lead? Model Ability and Task-Conditioned Collaboration with Humans
Paper • 2610.27148 • Published • 5
What Makes a Good Unmasking Policy? A Controlled Study of Learned Unmasking in Diffusion Language Models
Paper • 2610.31576 • Published • 5
RIDAR: Safeguarding Research Integrity in Autonomous Research Agents via Automated Detection and Runtime Intervention
Paper • 2610.31372 • Published • 8
MolLean: A Process-Verifiable Language for Chemical Reasoning
Paper • 2610.20459 • Published • 9
RTAformer: Relation-Transition-Aware Transformer for Video Scene Graph Generation
Paper • 2610.20091 • Published • 12
RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing
Paper • 2610.19705 • Published • 18
RLSplat: Resource-Linear Budget Control for Feed-forward 3D Gaussian Splatting
Paper • 2610.27712 • Published • 16
Heartbeat Thinking: Speculative Reasoning and Tool Execution While Listening in Realtime Voice Agents
Paper • 2610.26233 • Published • 18
What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models
Paper • 2610.23987 • Published • 33
IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems
Paper • 2610.30949 • Published • 86
WeVisOne-VL: Unified Visual Perception from Objects to Pixels
Paper • 2610.31329 • Published • 232
MambaAct: Efficient Mamba Action Experts for Flow-Matching Vision-Language-Action Models
Paper • 2610.22951 • Published • 3
Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective
Paper • 2610.12586 • Published • 1
SEAM: Spectral Embedding Alignment and Merging for Low-Resource TTS
Paper • 2610.26252 • Published • 2
Inherited, Not Invented: Tracing the Provenance of Wait in Reasoning Models
Paper • 2610.30882 • Published • 7
Cola2: Co-Adaptive Hierarchical Language Modeling with Continuous Semantic Compression and Balanced Discrete Generation
Paper • 2610.31305 • Published • 15