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 18 September 2026 to 6 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 196
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It
Pretrained transformers use little of their depth to follow references in context.SEED: Self-Speculative Decoding via Implicit Encoder-Decoder
Self-speculative decoding accelerates large language model (LLM) inference by drafting tokens from the target model itself, but faces a sharp tradeoff between the quality and cost of the draft.Act First, Reason Later: Accelerating On-Policy Distillation for Multi-Turn Agents via Reference-Conditioned Inverse Dynamics
On-policy distillation (OPD) trains multi-turn language agents with dense teacher supervision on student-generated responses.Generating Edit-Inducing Questions for AI Research Manuscripts
We study the ability of LLMs to generate edit-inducing questions whose answer will improve a paper draft.What Makes Recurrence Effective in Looped Language Models?
Looped language models (LoopLMs) increase computational depth through parameter sharing, offering a path to scale inference computation without adding parameters.Replay the Curvature: Accurate and Scalable NVFP4 Quantization for Large Language Model Inference
Large language models make weight storage and memory traffic major inference costs, motivating low-precision formats that represent each weight with only a few bits.Gödel Forest: Balancing Search Depth and Breadth for Data-Centric Recursive Self-Improvement
Recursive self-improvement (RSI) aims to achieve compounding gains by having models improve themselves.MARCO: Multi-Round Agentic Reinforcement for Conditional Molecular Optimization
Molecular optimization is inherently iterative: a candidate is proposed, evaluated against several objectives, and revised while preserving a relationship to the source molecule.ProgressCompass: Embodied Progress Reward Models Are Lost Without the Right Context
Embodied agents now take on ever longer tasks.CHAIN: Calibrated LLM Forecasting via Causal-Temporal Hypergraph Inference
Large language models have achieved significant progress in event forecasting, yet their probability outputs exhibit systematic calibration bias that varies heterogeneously across different domains…Video2Skill: From Streaming Experience to Reusable Embodied Skills
Manipulation behaviors vary widely across objects and scenes, but they share a small set of reusable skills, and planning with these skills helps embodied agents generalize to new tasks.Lost in Conversation or Lost in Translation? Diagnosing Multi-Turn Degradation in RAG
When conversing with large language models (LLMs), users often begin with a simple question and build towards a multi-hop question through follow-up turns.LAURA: Knowledge Distillation for Interpretable Ambiguous Clause Identification in Legal Contracts
Legal contracts contain ambiguities that expose enterprises to financial and legal risks.ATTUNER: Recomputation-Free KV Cache Reuse via Query-Side Adaptation
Large language model (LLM) agents repeatedly load reusable content, such as skills, documents, and memory entries, into the current context.Can Agents Design Libraries for Agents?
Agents increasingly build on code written by other agents, and they reimplement rather than reuse, growing the codebases later agents must work in.Distilling What Matters: Confidence-Aware Selective Distillation for Large Language Models
Knowledge Distillation (KD) trains a smaller-capacity student model to imitate a larger-capacity teacher model by matching output distributions, implicitly assuming the teacher to be a reliable…From Neurons to Conversation: Speech Brain-Computer Interfaces
Speech brain-computer interfaces (BCIs) aim to restore communication by transforming neural activity related to speech, language, or communicative intent into external outputs such as text…Reconstructing the Vocal Tract with Differentiable Acoustic Simulation
The vocal tract is the region of the human body responsible for filtering one's voice to create speech.Backpropagated Output Momentum: Relocating Optimizer History from Parameters to Task Space
Optimizer momentum is usually stored as a parameter-sized moving average of past gradients, which makes history costly and fixes each past signal in the coordinates in which it was computed.SIPO: Unifying Reinforcement Learning with On-Policy Self-Distillation
Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for improving large language models (LLMs) on various tasks, yet its sparse outcome rewards lack token-level…