Inference & Efficiency
A
Showing 31–60 of 127
-
TextSeal2: Distortion-Free LLM Watermarking with Copula Mixing and Memoryless Races
-
Every Token Needs Its Own Teacher: Multi-teacher Adaptive On-policy Self-distillation
-
Comparing Human Role-Players and LLM-Simulated Clients in Online Counselling Training: An Analysis of Counselling Patterns
-
On the Fundamental Limits of Prefill-Based Decoding Length Prediction
-
NEOPIC: A Neural Operator Framework for Particle-based Kinetic Plasma Simulations
-
IndicIPR-QA: A Benchmark for Extractive Question Answering on Indian IPR Laws
-
AI in the EGI e-infrastructure -- Past experiences and future strategies
-
Fast and accurate neural triage decoding of ultra-high-rate quantum LDPC codes
-
Soil Moisture Estimation in Precision Agriculture: A Knowledge Distillation Approach
-
Uncertainty-aware Feedback Loop Diagnosis: integrating reinforcement learning and conformal prediction for reliable wafer defect classification
-
Don't Lose the Thread: Empowering Long-Horizon LLM Agents with Cognitive Resource Self-Allocation
-
A Unified Hessian-Guided Framework for Post-Training Quantization
-
Radiology Guideline-derived Decision Graph for Efficient Clinical Decision Support
-
How to Loop Your Transformer: Loop Scaling, Specialization, and Parallel Inference
-
Rimuru: Unified Memory Management for Modern LLM Serving via Elastic Expert Offloading
-
DolphinRouting: Cluster-Level Binary Routing for Disaggregated LLM Inference Serving
-
Only Accepted Tokens Count: An Energy Accounting of Speculative Decoding Under Latency Targets
-
Latent Path Exploration via Potential-Guided Subtrajectory Balance
-
TaskFrame: Connecting Task-Level Planning with Frame-Level Control for Game Agents
-
ScienceJudge: Pattern Perturbation Augmentation for Sentence-Level Scientific Claim Verification
-
EpiAgent: Epistemic Self-Play for LLM Agents
-
Intelligence Report: SNSのAI分析からみる米中間選挙Sakana AI reads the Texas Senate race from 710K social media reactionsSakana AI analyzed about 710,000 reactions on X to the Texas Senate race. It estimates Paxton's pre-runoff support was largely party mobilization, dropping from about 50% to under 20% afterward, and that sentiment shifted two months before forecasters moved.
-
One Vector or Many? Clustered Optimal-Transport Steering under Quantization
-
Attention, Dynamic Wave and Hybrid Sequence Mixers in Language Models
-
KV Cache Quantization for Diffusion Language Models
-
Topology Survives Shuffling: Robust Long-Context Memory Access Prediction for Graph Analytics
-
Smooth Action Chunking Via Movement-Primitive Representations for Imitation Learning
-
LinQuant: Functional Invariances for Low-Precision Linear Recurrences
-
MulClip: A table-free activation function with monotonic and folding regimes for reservoir computing on microcontrollers
-
Learning to Bound: Monotonic, Calibrated Neural Upper Bounds for MPE Inference