Perplexity

Timeline

1. Oct 8, 2026 · Research paper · 1 source
   Looking Inside LLMs: Small-World Connectivity as a Signature of Reasoning Performance
   Inspired by neuroscience findings linking higher intelligence to stronger small-world organization in functional brain networks, we investigate small-world connectivity as a structural signature of LLM reasoning.
2. Oct 8, 2026 · Research paper · 1 source
   Read What Matters: Query-Adaptive Quantization for KV Caches
   KV-cache entries are stored before their future queries are known, but each decoding query needs precision in different places.
3. Oct 8, 2026 · Research paper · 1 source
   PIVOT: Perplexity-Informed KD-to-RL Transition Scheduling for Vertical-Domain Few-Shot Distillation
   We propose PIVOT (Perplexity-Informed Transition Optimization), a dynamic transition framework that routes samples between OPD and GRPO according to teacher-evaluated sequence perplexity.
4. Oct 7, 2026 · Research paper · 1 source
   HySPE: Positional Encoding via Symplectic Dual Shears
   We introduce Hyperbolic Symplectic Positional Encoding (HySPE), grounding positional attention in non-compact symplectic transformations.
5. Oct 7, 2026 · Research paper · 1 source
   Activation-Aware Weight Tensorization: A Calibration-Time Preconditioner for Tensor-Network LLM Compression
   We propose Activation-aware Weight Tensorization (AWT), a training-free calibration wrapper that preconditions each weight matrix with a diagonal activation-derived scale before an unchanged TT/TTN solver and deploys the result with only an input-side elementwise rescaling.
6. Oct 6, 2026 · Research paper · 1 source
   Few Bits, One Law: Toward W2A4KV2
   We introduce CanonQ, a unified quantization-aware training framework that addresses these challenges by separating source canonicalization from task-aware adaptation.
7. Oct 6, 2026 · Research paper · 1 source
   Denoising Hierarchical Representations: Joint Continuous Diffusion for Language Modeling
   In this work, we introduce Hierarchical Continuous Diffusion Language Models (H-CDLMs), a simple framework that further improves continuous DLMs with minimal compute and parameter overhead.
8. Oct 6, 2026 · Research paper · 1 source
   Align, Then Correct: Training-Free Two-Stage Low-Rank Compensation for Extremely Quantized Large Language Models
   Low-rank quantization error compensation (LQEC) recovers the accuracy lost under aggressive weight quantization by attaching a closed-form rank-$r$ adapter beside each frozen quantized weight, without any training.
9. Oct 6, 2026 · Research paper · 1 source
   Tiny-Scale Chinese BERT Pretraining: A Controlled Comparison of MLM, WWM, and MacBERT Strategies
   This paper presents a controlled comparison of these three strategies on a tiny-scale Chinese BERT model (4 layers, 256 hidden dimensions, 8.7M parameters).
10. Oct 5, 2026 · Model release · 1 source
    perplexity-ai/pplx-decider-v1.1-27b
    perplexity-ai published the model pplx-decider-v1.1-27b on Hugging Face.
11. Oct 1, 2026 · Product / feature launch · 1 source
    unslothai/unsloth v0.1.902-beta: Command Palette + Desktop UI/UX
    This release brings faster navigation, shareable run settings, and clearer errors to Unsloth Desktop.

Often appears with