127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “inference”

20,505 results

Research

Large Language Continuous Diffusion Models

DGX agent

arXiv:2610.02665v1 Announce Type: cross Abstract: Despite the success of discrete diffusion language models (dLMs) for fast parallel decoding, their non-smooth, high-dimensional space hinders trajecto

researcharxiv-cs-ai

5 Oct 2026

Local Ai

Search: “inference”

Large Language Continuous Diffusion Models

Less Talk. More Breakout: Kolibri-1 Turns Probabilities into Actions, Playing Breakout - With under 25ms latency per move.

LiteEMG-FM: An Efficient and Deployable Foundation Model for Robust EMG Sensing

Native Action-Prior Learning from Videos for World Action Models

NetApp’s Novus tackles metadata bottlenecks in AI data infrastructure

Post-Training Quantization of Autoregressive Weather Models

PsyEvo: A Personalized Counseling Agent That Self-Evolves at Test Time

Qwen3.8-Flash-Next (125B) on a single Strix Halo mini PC: 44-59 tok/s with speculative decoding, ~1,400 tok/s prefill, engine is open

Recursive Agent Optimization

Relevant Evidence Decoding for Audio-Visual Hallucination Mitigation

Reliability of Probabilistic Emulation of Physical Systems

ReSCUE: Re-translation with Sentence Commitment for Unsegmented Long-Form Simultaneous Sign Language Translation

Rethinking What to Cache in Few-Step Diffusion Transformers: Solver-Aware Target Selection

SecJev: Bringing Security Expertise to System One Decision Models

SlimKV: Joint Token-Feature KV Cache Compression with Reconstruction-Free Beacon Attention

T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images

Tangent Schrodinger Bridge Matching: Learning Stochastic Transport with Mechanistic Sensitivities

Transcriptome-informed multi-modal AI for predicting neoadjuvant therapy response from breast cancer biopsies

Y'all this is a sexy paper; context language models

ZeroMAG: Zero-Shot Multimodal Adapter Generation for Plug-and-Play EEG Foundation Models

I Distilled an LLM into two 287M encoders (GLiNER + multiple choice) for document extraction, can't match teacher. did i do something wrong?

Is Strix Halo (GMKtec EVO-X2, etc.) the closest thing we have to a 'dream' local LLM box?

Synthesis: Arxiv-Cs-Ai

I built Ninfer 4080 for 16GB class GPUs

Running Qwen3.8 Flash Next 176B on a 16GB RTX 3080 Laptop + 32GB RAM + SSD

Banger paper from NVIDIA on long running agents. A model can accept 128K tokens of context and still make more mistakes the longer it works …

Beyond Final Accuracy: Auditing Communication in LLM Multi-Agent Systems

Bootstrapping Video Interaction Generation with Synthetic State Transitions

CARM: Cancellation-Aware Response Masking for LLM Reinforcement Learning

ChunkVLA-AM: Parallel Action Chunking for Vision-Language-Action Robot Control in Additive Manufacturing

Counting Moves, Weighing Voices: Bayesian Dialectical Argumentation for Calibrated Multi-LLM Councils under Persistent Adversaries

Cross-Lingual Alignment for Decoder-Only Models using MoE Routers

DRelay: Global Draft Context for Prefix-Aware Parallel Speculative Decoding Repair

Emergent Unfaithfulness: How Alignment Training Causes Language Models to Silently Override Task Faithfulness

Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models

Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens

FlashBack: Knowing When to Remember in Streaming Vision-Language Models

GKE CPU startup boost: Accelerate app starts without over-provisioning

Hardware-Algorithm Co-Optimization of Early-Exit Neural Networks for Multi-Core Edge Accelerators

Harnessing Domain Specialists in Multimodal Mixture-of-Experts for Efficient Adaptation

Homomorphic Advantage Operator: Stabilizing Reinforcement Learning Under Fully Homomorphic Encryption Constraints

I benchmarked Qwen 3.8 27B on my M4 Max — here's what I learned about local models, context, and coding performance

ITC-MoE: Importance-guided Token-aware Compression for MoE Diffusion Language Models

Iterative Policy Refinement through Semantic Rollout Analysis

LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery

Learn the Directions, Normalize the Gains: Post-Training Normalization for LoRA

Managing Context and Communication in Distributed Agentic UAV Swarms

Match the Distribution, Not the Compute: Post-Training Multi-Token Prediction Heads