AI & Machine Learning · Computer Science & AI
Computation & Language / NLP
The newest papers in Computation & Language / NLP that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 17 September 2026 to 5 November 2026: 5,000 arXiv preprints.
Get the few papers worth your time in Computation & Language / NLP every morning.
Follow Computation & Language / NLP and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 83
DStill: Trajectory Consistency Distillation for Accelerated One-Step Drafting in Block Diffusion Speculative Decoding
Block-diffusion speculative decoding accelerates large language model inference by drafting multiple tokens in parallel.Steering intonational tunes in text-to-speech synthesis
Text-to-speech systems built on residual vector quantization often generate audio in two stages: a transformer backbone emits the first level of each frame's token stack, and a smaller depth model…More Memory, Worse Agents: Error Reproduction and Anti-Persistence in LLM Agents
LLM agents can improve across tasks without updating model parameters by storing experience from their own executions in external memory and reusing it to guide later decisions.Looking Into The Past: The Impact of Context on Detecting Deceptive Statements
Deception detection typically considers messages in isolation.Stable Signer V3: 4D Deformable Primitive Splatting Is All You Need for Sign Language Production
We present Stable Signer V3, an interactive high-resolution sign language avatar system built on 4D Deformable Primitive Splatting.What Can't Jev Decide? Probing the Limits of One-Pass Decision Models
Jev and its open replicas choose among the options a caller supplies with a single forward pass, fast enough to decide inside an agent loop.Epi: Towards a Persistent, Self-Improving Agent for Autonomous Research
We present Épi, an autonomous research agent that sustains investigations across model sessions and evolves its methods through accumulated experience. Épi combines persistent research history…Over-Defense in Coding Agents Begins at Silent Forks
Language models behind coding agents are post-trained with outcome rewards, and recent methods concentrate credit on the turns that decide the outcome.CasePlay: Self-Play Reinforcement Learning from Case Reports for Medical Reasoning
Reinforcement learning (RL) is a promising way to improve the clinical reasoning abilities of large language models (LLMs), but current pipelines often rely on expert-labeled questions or costly…Revealing what benchmark scores hide: Jointly measuring the breadth and reliability of LLM capabilities using accessibility profiles
Language model benchmarks assign each question a single outcome from one fixed wording, even though the same underlying request can be expressed in many equivalent ways.CoworkEnv: Synthesizing Training Environments for Long-Horizon Cowork Agents
AI coworkers must coordinate tools, communicate across turns, and act on changing workspace state while respecting workflow constraints.DeGMatch: Target-Aware Reasoning Data Selection via Deconfounded Gradient Matching
Reasoning post-training on long trajectories has substantially improved the reasoning capabilities of large language models, but scaling such training to large datasets is increasingly expensive.Rubrics Carry the Standard: Shapley Attribution for Checklist-Based LLM Judges
Checklist rubrics applied by large language model (LLM) judges have become a standard instrument for evaluating open-ended outputs and for rewarding them during training.A Measurement Perspective on Benchmarking LLM-Generated Text Detectors using Item Response Theory
Benchmarking large language model (LLM)-generated text detectors commonly relies on aggregate detector-level metrics such as accuracy, F1 score, and AUC.The World as Viewed by 136 Countries: An Open, Curated, Annotated, and Multilingual Dataset of 118 Million State Media Articles
State media outlets often project their governments' narratives to target both domestic and foreign audiences.Certified Sparse Attention via Perturbed Retrieval
Sparse attention speeds up long-context decoding by reading few keys of the KV cache, but existing methods do not control the error of a query, and on real KV caches their errors have heavy tails.When Does Better Acceptance Pay? A Controlled Study of Speculative Decoding
The throughput gains of speculative decoding depend on the trade-off between acceptance length and execution latency.SoK: PIAtlas: Decomposing the Unbounded Prompt Injection Attack Space
Prompt injection is the dominant security risk for large-language-model (LLM) applications and agents, yet the field still lacks a coherent map of how these attacks are constructed.One Head Away from Language Confusion: Single Attention Heads Across Model Families
Large language models sometimes reply in an unexpected language, a failure known as language confusion.Beyond the Teacher: Understanding and Preserving Distillation Overshoot in Agentic On-Policy Distillation
On-policy distillation (OPD) trains agents on their own trajectories using supervision from a stronger teacher.