Large Language Models

arXiv:2601.04823v4 Announce Type: replace Abstract: Mixture-of-Experts (MoE) has become a prominent paradigm for scaling Large Language Models (LLMs). Parameter

arXiv:2601.05144v2 Announce Type: replace Abstract: Reasoning Large Language Models (RLLMs) excelling in complex tasks present unique challenges for digital wat

arXiv:2602.08734v2 Announce Type: replace Abstract: Solving partially observable Markov decision processes (POMDPs) requires computing policies under imperfect

arXiv:2602.19837v2 Announce Type: replace Abstract: Humans are highly effective at utilizing prior knowledge to adapt to novel tasks, a capability that standard

arXiv:2602.22413v2 Announce Type: replace Abstract: We investigate the collective accuracy of heterogeneous agents who learn to estimate their own reliability o

arXiv:2603.04636v2 Announce Type: replace Abstract: Despite their wide-ranging benefits, LLM-based agents deployed in open environments can be exploited to prod

arXiv:2502.14883v3 Announce Type: replace-cross Abstract: For individuals with blindness or low vision (BLV), navigating complex environments can pose serious r

arXiv:2505.15808v2 Announce Type: replace-cross Abstract: We present a neural framework for learning conditional optimal transport (OT) maps between probability

arXiv:2505.17760v3 Announce Type: replace-cross Abstract: LLM-as-a-judge is widely used as a scalable substitute for human evaluation, yet current approaches re

arXiv:2505.19715v2 Announce Type: replace-cross Abstract: Recently, the pretrain-finetune paradigm has become a cornerstone in various deep learning areas. Whil

arXiv:2505.21505v3 Announce Type: replace-cross Abstract: Multilingual Alignment is an effective and representative paradigm to enhance LLMs' multilingual capab

arXiv:2506.09354v2 Announce Type: replace-cross Abstract: Mental health is a growing global concern, prompting interest in AI-driven solutions to expand access

arXiv:2506.18919v4 Announce Type: replace-cross Abstract: As a multimodal medium combining images and text, memes frequently convey implicit harmful content thr

arXiv:2508.07629v4 Announce Type: replace-cross Abstract: We present Klear-Reasoner, a model with long reasoning capabilities that demonstrates careful delibera

arXiv:2508.17431v2 Announce Type: replace-cross Abstract: Person re-identification (re-ID) is a fundamental task in intelligent surveillance and public safety.

arXiv:2509.25424v4 Announce Type: replace-cross Abstract: Reinforcement learning fine-tuning (RLFT) is a dominant paradigm for improving pretrained policies for

arXiv:2510.00766v2 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) demonstrate a promising direction for assisting individuals with

arXiv:2510.02226v3 Announce Type: replace-cross Abstract: Recent advances in generative video models have enabled the creation of high-quality videos based on n

arXiv:2510.06545v2 Announce Type: replace-cross Abstract: We investigate mathematically the notion of incoherence: a structural issue with reinforcement learnin

arXiv:2510.25770v2 Announce Type: replace-cross Abstract: While generative models, especially large language models (LLMs), are ubiquitous in today's world, pri

arXiv:2511.08225v2 Announce Type: replace-cross Abstract: As teachers increasingly turn to GenAI in their educational practice, we need robust methods to benchm

arXiv:2511.20224v2 Announce Type: replace-cross Abstract: Audio tokenization bridges continuous waveforms and multi-track music language models. In dual-track m

arXiv:2511.20836v3 Announce Type: replace-cross Abstract: As language models (LMs) are increasingly adopted across domains, high-quality benchmarking frameworks

arXiv:2512.00234v2 Announce Type: replace-cross Abstract: There has been significant progress in open-source text-only translation large language models (LLMs)

arXiv:2512.02966v2 Announce Type: replace-cross Abstract: We introduce the first principled framework, Lumos, for specifying and formally certifying Language Mo

arXiv:2602.00750v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used in interactive and retrieval-augmented systems, but

arXiv:2602.06801v4 Announce Type: replace-cross Abstract: Activation steering methods are widely used to control large language model (LLM) behavior and are oft

arXiv:2602.08040v3 Announce Type: replace-cross Abstract: Deep neural networks trained on nonstationary data must balance stability (i.e., retaining prior knowl

arXiv:2602.13851v2 Announce Type: replace-cross Abstract: Formal specifications are crucial for building verifiable and dependable software systems, yet generat

arXiv:2602.18807v2 Announce Type: replace-cross Abstract: We evaluate GPTutor, an LLM-powered tutoring system for an undergraduate discrete mathematics course.

arXiv:2603.17205v2 Announce Type: replace-cross Abstract: Domain-specific finetuning is essential for dense retrievers, yet not all training pairs contribute eq

Introduction "AI coding tools and resources are scattered everywhere. A topically organized, searchable, contributable list can save enormous amounts of search

How I Built Cryptographic Signing for Every AI Agent Tool Call Your AI agent just mass-deleted a production database. Can you prove exactly what it did? When? W

The AI landscape is experiencing unprecedented growth and transformation. This post delves into the key developments shaping the future of artificial intelligen

It feels like spring has sprung here, and so has a new NVIDIA integration, ticket sales for Interrupt 2026, and announcing LangSmith Fleet (formerly Agent Build

Artificial intelligence has an important role to place in improving climate finance flows, and the climate finance world has a role to play in shaping AI govern

Your agent hits a rate limit. The fallback logic kicks in, picks an alternative model. Everything should be fine. Except the request still goes to the original

Fourteen Angstroms A silicon atom is roughly 2 angstroms in diameter. Fujitsu is building transistors at 14 angstroms -- 1.4 nanometers -- for a neural processi

AI search recommends only 1.2% of local businesses. 68% of its business info is wrong. Consumers aren't checking. Nobody is measuring this failure — because the

If you're building a shopping or price comparison agent with OpenClaw, Amazon alone isn't enough. A lot of US retail happens at Walmart — and Walmart has data A

Comments

The AI landscape is experiencing unprecedented growth and transformation. This post delves into the key developments shaping the future of artificial intelligen

Everything after # is invisible to the user. But if an AI includes the full URL in its context, that hidden fragment becomes part of the prompt. The result? Bia

A new study from researchers at UC Berkeley and UC Santa Cruz suggests models will disobey human commands to protect their own kind.

Star Wars producer Kathleen Kennedy was one of the few skeptics at the Runway AI Summit, where AI was compared to fire and the printing press just a week after

Anthropic and DoD are in a battle over the acceptable military use of AI models. The case highlights tensions between AI safety, ethics and national security.

AI benchmarks report how large language models (LLMs) perform on specific tasks but provide little insight into their underlying capabilities that drive their p

The firm says it can reduce the cost of chip development by more than 75% and cut the timeline by more than half.