Research Paper

Making Voice Assistants Faster Without Losing Accuracy

Making Voice Assistants Faster Without Losing Accuracy

Have you ever noticed how some voice assistants seem to understand you instantly, while others leave you waiting? That delay isn't random. It's the result of a fundamental trade-off that has plagued speech recognition for years. Systems could either be fast or accurate, but rarely both.

Semantic Highlighting: Making RAG Cheaper Without Compromises

Semantic Highlighting: Making RAG Cheaper Without Compromises

Recent research from the Zilliz team tackles a problem that shows up constantly in production RAG systems: how do you actually show users why a document is relevant to their query? Consider a typical scenario. A user asks: "How can I speed up my Python code?" The vector

The Discipline Layer: Harnesses as the Missing Piece in Autonomous Coding

The Discipline Layer: Harnesses as the Missing Piece in Autonomous Coding

Introduction If you've been working with AI agents on longer tasks, you've probably developed your own tricks for dealing with context window limits. Maybe you hit /summarize in Cursor when things get bloated or you ask the agent to write a summary.md file at the

Breaking the Context Window: How Recursive Language Models Handle Infinite Input

Breaking the Context Window: How Recursive Language Models Handle Infinite Input

Long-context understanding has been a persistent challenge in language model research. Despite architectural innovations (ALiBi, YaRN, RoPE variants) and massive context window expansions (Claude 3.5 at 200k tokens, GPT-5 at 256k+), models still exhibit performance degradation on long inputs, a phenomenon known as "context rot." The community

Kimi K2 Thinking: Engineering Deep Reasoning at Scale

Kimi K2 Thinking: Engineering Deep Reasoning at Scale

Introduction Moonshot AI recently open-sourced Kimi K2 and its reasoning-optimized variant, K2 Thinking. As someone who works with large language models, I wanted to break down what makes this release interesting and where it pushes forward the state of open-source AI. K2 Thinking is a 1-trillion parameter model that can

AgentFold : What If AI Agents Managed Memory Like Humans Do?

AgentFold : What If AI Agents Managed Memory Like Humans Do?

Introduction If you've spent time working with LLM agents for web research, coding assistance in cursor or even extended conversations in ChatGPT, you've probably noticed something: as tasks or multi turn conversations grow longer and more complex, the quality of responses deteriorates - essentially because of

FastLongSpeech: 30x Compression That Doesn't Murder Your Context

FastLongSpeech: 30x Compression That Doesn't Murder Your Context

Speech models are having a moment and seems like they’re here to stay. They can transcribe your rambling, understand your questions, and even tell when you're being sarcastic. But ask them to process anything longer than a TikTok video and they straight-up collapse. The problem? Speech can

Chain-Talker: Teaching AI to Speak with Empathy

Chain-Talker: Teaching AI to Speak with Empathy

When AI systems engage in conversation, getting the words right is only half the battle. The real challenge is emotional appropriateness: responding to "I just lost my job" with genuine sympathy rather than robotic cheerfulness, or matching enthusiasm when someone shares good news. Current conversational speech synthesis (CSS)

DiTTo-TTS: The TTS System That Doesn't Need Your Phonemes (And Why That's a Big Deal)

DiTTo-TTS: The TTS System That Doesn't Need Your Phonemes (And Why That's a Big Deal)

Text-to-speech has always been that one AI domain where you couldn't just throw data at the problem and call it a day. “Data is the moat” is straight up not a thing here. Want to build a TTS system? Better get comfortable with phonemizers, forced aligners, duration predictors,

Are Small Language Models the Future of Agentic AI?

Are Small Language Models the Future of Agentic AI?

Recent research from NVIDIA presents a compelling argument that small language models (SLMs) represent the future of agentic artificial intelligence systems. The paper challenges the current industry paradigm of deploying large language models for all agent tasks, proposing instead that smaller, specialized models offer superior operational characteristics for most agentic

What GenSE Gets Right For LLM-Assisted Speech Enhancement 🎙️

What GenSE Gets Right For LLM-Assisted Speech Enhancement 🎙️

Speech enhancement, the art of cleaning up noisy, muffled, or degraded audio, has traditionally been the domain of signal processing algorithms and convolutional networks. But what if we treated speech cleaning like a language problem instead? That's exactly what researchers from Northwestern Polytechnical University and Nanyang Technological University

Best LLMs for Legal AI Agents: A Deep Dive into LegalBench Performance

Best LLMs for Legal AI Agents: A Deep Dive into LegalBench Performance

From contract analysis to legal research, from compliance monitoring to case preparation, artificial intelligence is transforming how legal professionals work. However, the stakes in legal practice are uniquely high. A single error can result in malpractice claims, regulatory violations, or adverse case outcomes. This reality makes choosing the right AI

PaperBench: Can AI Agents Actually Replicate AI Research?

PaperBench: Can AI Agents Actually Replicate AI Research?

Model's Replication Scores Average Replication Scores on PaperBench

OS-HARM: The AI Safety Benchmark That Puts LLM Agents Through Hell

OS-HARM: The AI Safety Benchmark That Puts LLM Agents Through Hell

Language models have come a long way. From playing autocomplete in your email to writing decent Python scripts, they’ve now levelled up into agents: full-blown task-doers who can click, scroll, type, and wreak havoc across your desktop. These “computer use agents” are smart enough to open your emails, edit

Tool Chaos No More: How We’re Measuring Model-Tool Accuracy in the Age of MCP

Tool Chaos No More: How We’re Measuring Model-Tool Accuracy in the Age of MCP

Introduction Picture this scenario: you’ve built an AI agent, given it access to dozens of tools, and deployed it to handle a complex workflow. But instead of executing queries crisply, it’s making redundant tool calls, burning API credits needlessly, and overcomplicating straightforward processes. This isn’t just an