KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving
Paper • 2605.13734 • Published • 11
Urro PRO
urroxyz
AI & ML interests
computational linguistics major 🤖🔎ðŸ”
i am autistic. if i come off rude, i probably didn't mean to. please feel free to ask me for clarification.
Recent Activity
upvoted a paper about 3 hours ago
KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving updated a collection about 3 hours ago
WTF GENIUS PAPERS upvoted a paper about 3 hours ago
Forecasting Downstream Performance of LLMs With Proxy MetricsOrganizations
upvoted a paper about 3 hours ago
updated a
collection about 3 hours ago
upvoted 2
papers about 3 hours ago
updated a
collection about 3 hours ago
upvoted 4
papers about 4 hours ago
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
Paper • 2605.16928 • Published • 89
Ï€-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
Paper • 2605.14678 • Published • 97
Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?
Paper • 2605.22109 • Published • 164
TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation
Paper • 2605.22355 • Published • 171
updated a
collection about 4 hours ago
upvoted a paper about 4 hours ago
updated a
collection about 4 hours ago
upvoted 5
papers about 4 hours ago
The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation
Paper • 2605.21856 • Published • 3
HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents
Paper • 2605.17873 • Published • 4
The Expense of Seeing: Attaining Trustworthy Multimodal Reasoning Within the Monolithic Paradigm
Paper • 2604.20665 • Published • 5
Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR
Paper • 2605.19282 • Published • 6
LatentUMM: Dual Latent Alignment for Unified Multimodal Models
Paper • 2605.17766 • Published • 6
updated a
collection about 4 hours ago
upvoted 2
papers about 4 hours ago