Category
9,568 papers
The ABAI submission to COLIEE 2026 Task 1, case law retrieval is presented, together with a controlled study of why it underperformed, and four evaluation artifacts are document, each of which reversed a result once the protocol was corrected.
WatchPoint is introduced, a simulated-user system that mimics real developer behavior by generating and executing diagnostic scripts against the running application, producing structured observations that guide the coding model's retry and identifies a pattern of capability gaps that governs when simulated-user feedbac...
Experiments demonstrate that DDPO significantly outperforms static prompt optimization methods, particularly on weakly aligned models and when handling semantically ambiguous benign prompts, successfully distinguishing them from genuinely harmful requests.
The results show that weight-only statistical scoring can match or outperform data-dependent methods for structured head pruning, providing a practical, zero-cost criterion for Transformer compression.
Reach audiences
Advertise in front of researchers, engineers, and readers.
TSS, a target-side sparsification framework for speculative decoding that employs an acceptance- and metric-aware breadth search to explore multi-layer skip configurations without imposing a fixed priority between the two objectives, is proposed.
Applying large language models to Traditional Chinese Medicine (TCM) prescription generation reveals three clinically critical gaps: models produce end-to-end mappings without auditable reasoning following the li-fa-fang-yao paradigm (SR Gap), treat each encounter in isolation without follow-up adjustment via sui zheng...
Language models are increasingly trained on the outputs of other models, forming chains that the authors call lineages, in which a trait present in one generation can pass to the next, and whether such a trait holds or fades across lineages is studied.
A Context-to-Answer-Aligned Memory Compression (CMC) framework is proposed, which compresses long input contexts into compact Context Memory Embeddings aligned to any frozen decoder's embedding space, reducing inference costs without modifying decoder weights.
Deploying Large Language Models for runtime operational triage incurs prohibitive latency (>100-500 ms), high VRAM requirements (>4-8 GB), and excessive energy dissipation. Extending Mandelbrot Fractal Neural Synthesis (Dagli et al., 2026), this paper presents the Universal Fractal Natural Language Decision Map, realiz...
This work studies parallel coding agents' failures with stale, a benchmark for semantic coordination, and finds that among 834 runs on 417 mined Django pairs, only one showed interference after correcting the grading procedure.
This work ran four frontier agents end to end end to end on metered L40S, A100, and H200 GPUs across 8B to 70B open bases, certifying every scenario before scoring, and ran a human FDE arm under the same oracle and compare every agent against it.
Viewing the field through this developmental lens, this survey provides a comprehensive synthesis of existing work, an insightful narrative of its trajectory, and a clear roadmap for future innovation in responsible, effective, and human-centered AI for mental healthcare.
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.
