AI research papers.

Large language model agents can often make reasonable local decisions on short tasks, yet their performance degrades when success requires long sequences of dependent actions and tool calls.

We introduce the Extender, a log-structured variant of the standard Transformer architecture.

Multidisciplinary tumor boards integrate multimodal clinical observations and longitudinal patient histories through specialist discussions, yet benchmarks rarely capture these real-world trajectories.

Fast matrix multiplication algorithms keep the product fixed and search for a cheaper way to evaluate it.

Model merging efficiently combines specialized large language models (LLMs) without joint retraining, but can substantially alter expert routing in Mixture-of-Experts (MoE) models.

A foundation model should not act in isolation as an embodied agent.

Recent progress in frontier models has renewed interest in large-scale reinforcement learning (RL), but the cost of generating large-model rollouts makes even testing RL recipes expensive.

Browser-use agents often carry information in their context as they move between websites.

We introduce Adaptive LeWorldModel (ALeWM), a world model based on a joint-embedding predictive architecture (JEPA) that learns to concentrate predictive information in compact prefixes of a wide latent representation.

Multiple agents may often conflict in an organization: for example, one coding agent changes an interface in a repository, but another continues to develop on the old version where existing tests become stale.

Multi-step agents are trained on flat action streams: SFT and RLVR weight every token uniformly and ignore the sub-procedures that recur across tasks, the hierarchy that lets humans plan top-down from reusable routines.

Paired synthetic aperture radar (SAR) and electro-optical (EO) imagery is increasingly available across sensors, resolutions, and geographic regions.

Evaluating recommender systems before deployment requires simulators that remain realistic over long, closed-loop interaction cycles.

Sparse attention visits few keys, yet finding them can still require scoring every key with every indexer head.

Interactive CAPTCHAs remain challenging for computer-use agents, while existing datasets face trade-offs among type coverage, interaction fidelity, and trajectory supervision.

arXiv:2606.03159v3 Announce Type: replace-cross Abstract: As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck.

arXiv:2609.25176v2 Announce Type: replace-cross Abstract: Real-time voice assistants must reason over evolving requests, execute actions, and follow conversational rules.

A main promise of looped language models is depth-adaptive inference.

Reliable progress in offline policy learning depends on careful reporting, well-tuned baselines, and evaluation across diverse conditions.

Streaming video understanding requires models to interpret evidence as it arrives, yet current evaluations often report task scores without specifying when evidence becomes valid, how visual history is maintained, or how…

Multi-teacher on-policy distillation (MOPD) integrates specialized capabilities into a single student, but existing practice typically hard-routes each prompt to a domain-matched teacher for the entire rollout.

Difference-in-differences (DID) studies are widely used to evaluate climate policy, but assessing the evidence supporting their identification assumptions remains challenging.

Open rerankers trained for general web retrieval transfer imperfectly to e-commerce, where ranking decisions depend not only on topical relevance but also on user preferences, product constraints, and comparative product…

Post-training quantization (PTQ) is a practical approach to reducing the memory and computational footprint of large language models (LLMs) without retraining.

Scaling language models to long contexts is limited by the quadratic cost of self-attention.

Large-scale Digital Surface Models (DSMs) can be produced cost-effectively from satellite images via stereo-photogrammetry.

Large vocabularies make output heads a substantial inference cost in small language models.

World Action Models (WAMs) jointly model visual dynamics and action generation for generalist robot manipulation.

We introduce Kaggle Game Arena, an open and ever-expanding platform to evaluate large language models (LLMs) through competitive games.

Existing multi-agent benchmarks primarily test in competitive settings, short-horizon interactions under 20 steps, or simply aggregate individual performance, failing to isolate and highlight genuine collaboration capabi…

Representation autoencoders (RAEs) reuse features from a pretrained visual encoder as reconstruction and diffusion latents, integrating strong visual representations into image generation.

General-purpose agents can plan, reason, and act over long horizons, yet their production capabilities remain fragmented across text, images, audio, video, documents, 3D assets, and code.

While modern text-to-speech (TTS) systems generate highly natural speech and support inline non-verbal vocalization (NVV) tags, accurate control over these events remains challenging.

Real-time full-duplex speech models can listen while speaking, enabling natural interaction without rigid turn boundaries.

Decentralized multi-agent path finding (MAPF) with communication requires agents to reach individual goals without collisions under partial observability.

Multi-agent systems distribute large contexts across agents that communicate to solve a task.

Macroeconomic productivity metrics, such as Total Factor Productivity, register technological breakthroughs with multi-year reporting lags due to administrative survey intervals and national accounting conventions.

Omni-modal agents must seek evidence across video, audio, web pages, and computation to answer questions.

We present LightMIS, a scalable family of ultra-lightweight convolutional networks for 2D binary medical image segmentation without a learned stage-wise decoder.

Few-step autoregressive (AR) video diffusion enables low-latency streaming generation, but existing post-training methods predominantly rely on Distribution Matching Distillation (DMD), requiring both a large pretrained…

In this paper, we propose RGBD20K, a novel dataset for facilitating the development of more robust and general RGB-D semantic segmentation by encompassing abundant categories and high-quality annotations.

Tool-calling agents produce heterogeneous outputs, interleaving structured tool invocations with user-facing natural language summaries.

In cross-lingual zero-shot text-to-speech, the accent of the reference leaks into the target speech.

Banking assistants must use account-specific information to answer requests and, in many cases, take actions through tools.

We find that language models can transfer capabilities through task-unrelated text.

Sparse AutoEncoders (SAEs) offer a promising way to inspect language model representations, but it is still unclear what kind of linguistic structure their latents expose.

Rufus-Air is an open and reproducible post-training recipe on GLM-4.5-Air-Base (106B-A12B), organized as a serial pipeline of eight stages: SFT, Reasoning RL, Coding RL, Instruction-Following RL, General Agent, Coding Ag…

Detectors of alignment failures screen deployed language models and score alignment benchmarks.