Category
9,568 papers
This work introduces LongPuzzleBench, 114 levels in six puzzle games played through native GUI actions, where one objective can take a human over a thousand actions on persistent boards and dead ends go unannounced.
ESCD aggregates prefix-related teacher events and supervises the total probability of byte-compatible one-step student completions, avoiding tokenizer-dependent probability splits among individual tokens, and support event entry and event completion as complementary supervision targets for cross-tokenizer knowledge tra...
This work systematically evaluates 15 LLMs spanning three model generations as both generators and detectors, revealing that detection efficacy is primarily driven by detector capability rather than generator provenance, although outputs from newer generators remain notably harder to detect.
RoSh is proposed, a per-language shift and rotation of the residual stream, computed in closed form at three layers, with no training and no weight modified, that improves every model and closes 75% of the gap on average, helping most where the model was worst.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This paper presents a shared task for in-game toxic language detection built upon real-world in-game chat data, and proposes the best-preforming model for the toxic language slot filling: Bi-directional Representations with Attention Residuals (BRAR).
This work introduces ActionLens, a diagnostic benchmark of 6,701 multiple-choice video questions spanning five targeted diagnostics: transition detection, actor-specific identification, concurrent action binding, directed interaction reasoning, and gaze detection, and diagnostic measurements of these distinct failure m...
RIME is introduced, a retrieval-induced memory framework that shifts memory construction from monolithic compression toward evidence-centered integration and consistently achieves the best performance across all three quality metrics among the compared methods, while requiring substantially fewer query-time LLM tokens.
AgentHop, a diagnostic benchmark of 1,011 multiple-choice questions paired with a controlled seven-tool sandbox under fixed token, turn, and tool-call constraints, and the full benchmark set and the harness are released to support diagnostic agent benchmarking.
Topic segmentation structures spoken documents into coherent sections, facilitating navigation and downstream understanding. The appropriate granularity can vary substantially, ranging from broad thematic shifts to fine-grained subtopics. Existing LLM-based segmenters, however, often struggle to adapt to this variation...
Coding Agent Memory Gym (CAMG), a suite of long-horizon agentic-RL environments spanning Shop, Coding, DeepResearch, and AutoResearch, which provides executable shell access and an episode-persistent workspace, enabling agents to create, revise, search, and reuse files as memory throughout an episode.
Just-In-Time Agent Memory (JAM), a trainable framework for query-conditioned context construction at runtime, is proposed, where it achieves stronger task performance than AOT-style memory systems while remaining substantially more efficient than prior trained agentic memory approaches.
We describe our system for DocSem, the document-grounded quantitative reasoning shared task at DocInsights 2026, and analyze why it succeeded on labeled data and failed on the test set. The pipeline pairs hybrid block retrieval with Program-of-Thoughts (PoT) generation executed in a sandboxed interpreter, self-consiste...
Natural Language Processing
Our most capable vision-language-action model enhances robot dexterity, reliability, and safety
A Blog post by Ai2 on Hugging Face
A Blog post by IBM Research on Hugging Face
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
