Microsoft

LLM can Read Spectrogram: Encoder-free Speech-Language Modeling

Recent speech-aware large language models (Speech-LLMs) rely on a pre-trained speech encoder to convert audio into semantic-rich representations consumable by LLM. In this work, instead, we explore: ...
AOL

Tensordyne Claims Massive Speed and Power Improvement Over Nvidia

If simulations are to be believed, startup Tensordyne's new AI chip could crush the performance of market leader Nvidia in terms of energy efficiency and latency for inferencing. The company just sent ...
VentureBeat

Context compression finally works in production: new research cuts LLM input 16x without the accuracy hit

Context windows are becoming a computational bottleneck. The longer an agent runs, the more tokens accumulate from retrieved documents, reasoning traces and conversation history, and the more memory ...
IEEE

Visual Evidence-aware for Object Hallucinations Rectification in LLM-based Video Captioning

Abstract: Recent neural models for video captioning are typically built using a framework that combines a pre-trained visual encoder with a large language model(LLM) decoder. However, large language ...
IEEE

Towards Effective and Efficient Non-Autoregressive Decoders for Conformer and LLM-Based ASR Using Block-Based Attention Mask

Abstract: Automatic speech recognition (ASR) systems often rely on autoregressive (AR) Transformer decoder architectures, which limit efficient inference parallelization due to their sequential nature ...
Geeky Gadgets

Why Prompt Caching is the Secret to Slashing Your AI Costs By 90%

Prompt caching has become a vital strategy for managing the rising costs of large language model (LLM) operations. By reusing previously computed data, this approach minimizes redundant computations, ...
Impacts

The 2026 LLM API Pricing Comparison: GPT-5.5, Claude Sonnet 4.6, Gemini 3.5 Flash and DeepSeek V4

Pricing is the single most consequential decision in choosing a frontier LLM, and it is also the dimension where most published comparisons are out of date within a quarter. This article cuts through ...
Scientific American

A third of Americans say they’ve asked AI to decode their medical results

When Judith Miller received the results of a medical imaging study last year, the 77-year-old Wisconsin resident did what many patients nowadays do: she asked AI to explain them. Claude, a large ...
InfoQ

Cloudflare Builds High-Performance Infrastructure for Running LLMs

Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with content, and download exclusive resources. Erik Steiger discusses the operational pain ...
Semiconductor Engineering

Microarchitecture Tailored to 3D-Stacked Near-Memory Processing LLM Decoding (U. of Edinburgh, Peking U., Cambridge et al.)

A new technical paper, “Rethinking Compute Substrates for 3D-Stacked Near-Memory LLM Decoding: Microarchitecture-Scheduling Co-Design,” was published by researchers at University of Edinburgh, Peking ...
VentureBeat

Monitoring LLM behavior: Drift, retries, and refusal patterns

Traditional software is predictable: Input A plus function B always equals output C. This determinism allows engineers to develop robust tests. On the other hand, generative AI is stochastic and ...