$S^3$: Stratified Scaling Search for Test-Time in Diffusion Language Models
arXiv:2604.06260v1 Announce Type: new
Abstract: Test-time scaling investigates whether a fixed diffusion language model (DLM) can generate better outputs when given more inference compute, without additional training. However, naive best-of-$K$ sampling is fundamentally limited because it repeatedl...
Spectral Edge Dynamics Reveal Functional Modes of Learning
arXiv:2604.06256v1 Announce Type: new
Abstract: Training dynamics during grokking concentrate along a small number of dominant update directions -- the spectral edge -- which reliably distinguishes grokking from non-grokking regimes. We show that standard mechanistic interpretability tools (head at...
FLeX: Fourier-based Low-rank EXpansion for multilingual transfer
arXiv:2604.06253v1 Announce Type: new
Abstract: Cross-lingual code generation is critical in enterprise environments where multiple programming languages coexist. However, fine-tuning large language models (LLMs) individually for each language is computationally prohibitive. This paper investigates...
Probabilistic Language Tries: A Unified Framework for Compression, Decision Policies, and Execution Reuse
arXiv:2604.06228v1 Announce Type: new
Abstract: We introduce probabilistic language tries (PLTs), a unified representation that makes explicit the prefix structure implicitly defined by any generative model over sequences. By assigning to each outgoing edge the conditional probability of the corres...
A Benchmark of Classical and Deep Learning Models for Agricultural Commodity Price Forecasting on A Novel Bangladeshi Market Price Dataset
arXiv:2604.06227v1 Announce Type: new
Abstract: Accurate short-term forecasting of agricultural commodity prices is critical for food security planning and smallholder income stabilisation in developing economies, yet machine-learning-ready datasets for this purpose remain scarce in South Asia. Thi...
Weakly Supervised Distillation of Hallucination Signals into Transformer Representations
arXiv:2604.06277v1 Announce Type: new
Abstract: Existing hallucination detection methods for large language models (LLMs) rely on external verification at inference time, requiring gold answers, retrieval systems, or auxiliary judge models. We ask whether this external supervision can instead be di...
LaCy: What Small Language Models Can and Should Learn is Not Just a Question of Loss
This paper was accepted at the Workshop on Memory for LLM-Based Agentic Systems at ICLR.
Language models have consistently grown to compress more world knowledge into their parameters, but the knowledge that can be pretrained into them is upper-bounded by their parameter size. Especially the capaci...
A Theoretical Framework for Acoustic Neighbor Embeddings
This paper provides a theoretical framework for interpreting acoustic neighbor embeddings, which are representations of the phonetic content of variable-width audio or text in a fixed-dimensional embedding space. A probabilistic interpretation of the distances between embeddings is proposed, based o...
Algebraic Structure Discovery for Real World Combinatorial Optimisation Problems: A General Framework from Abstract Algebra to Quotient Space Learning
arXiv:2604.04941v1 Announce Type: new
Abstract: Many combinatorial optimisation problems hide algebraic structures that, once exposed, shrink the search space and improve the chance of finding the global optimal solution. We present a general framework that (i) identifies algebraic structure, (ii) ...
Operational Noncommutativity in Sequential Metacognitive Judgments
arXiv:2604.04938v1 Announce Type: new
Abstract: Metacognition, understood as the monitoring and regulation of one's own cognitive processes, is inherently sequential: an agent evaluates an internal state, updates it, and may then re-evaluate under modified criteria. Order effects in cognition are w...
Pramana: Fine-Tuning Large Language Models for Epistemic Reasoning through Navya-Nyaya
arXiv:2604.04937v1 Announce Type: new
Abstract: Large language models produce fluent text but struggle with systematic reasoning, often hallucinating confident but unfounded claims. When Apple researchers added irrelevant context to mathematical problems, LLM performance degraded by 65% Apple Machi...
Governance-Aware Agent Telemetry for Closed-Loop Enforcement in Multi-Agent AI Systems
Enterprise multi-agent AI systems produce thousands of inter-agent interactions per hour, yet existing observability tools capture these dependencies without enforcing anything. OpenTelemetry and Langfuse collect telemetry but treat governance as a downstream analytics concern, not a real-time enfor...
This new chip survives 1300°F (700°C) and could change AI forever
A team of engineers has created a breakthrough memory device that keeps working at temperatures hotter than molten lava, shattering one of electronics’ biggest limits. Built from an unusual stack of ultra-durable materials, the tiny component can store data and perform calculations even at 700°C (13...
Toward Full Autonomous Laboratory Instrumentation Control with Large Language Models
arXiv:2604.03286v1 Announce Type: new
Abstract: The control of complex laboratory instrumentation often requires significant programming expertise, creating a barrier for researchers lacking computational skills. This work explores the potential of large language models (LLMs), such as ChatGPT, and...
IC3-Evolve: Proof-/Witness-Gated Offline LLM-Driven Heuristic Evolution for IC3 Hardware Model Checking
arXiv:2604.03232v1 Announce Type: new
Abstract: IC3, also known as property-directed reachability (PDR), is a commonly-used algorithm for hardware safety model checking. It checks if a state transition system complies with a given safety property. IC3 either returns UNSAFE (indicating property viol...
To Throw a Stone with Six Birds: On Agents and Agenthood
arXiv:2604.03239v1 Announce Type: new
Abstract: Six Birds Theory (SBT) treats macroscopic objects as induced closures rather than primitives. Empirical discussions of agency often conflate persistence (being an object) with control (making a counterfactual difference), which makes agency claims dif...
Position: Science of AI Evaluation Requires Item-level Benchmark Data
arXiv:2604.03244v1 Announce Type: new
Abstract: AI evaluations have become the primary evidence for deploying generative AI systems across high-stakes domains. However, current evaluation paradigms often exhibit systemic validity failures. These issues, ranging from unjustified design choices to mi...
Integrating Artificial Intelligence, Physics, and Internet of Things: A Framework for Cultural Heritage Conservation
arXiv:2604.03233v1 Announce Type: new
Abstract: The conservation of cultural heritage increasingly relies on integrating technological innovation with domain expertise to ensure effective monitoring and predictive maintenance. This paper presents a novel framework to support the preservation of cul...
arXiv:2604.03335v1 Announce Type: new
Abstract: Apparent age estimation is a valuable tool for business personalization, yet current models frequently exhibit demographic biases. We review prior works on the DEX method by applying distribution learning techniques such as Mean-Variance Loss (MVL) an...
DRAFT: Task Decoupled Latent Reasoning for Agent Safety
arXiv:2604.03242v1 Announce Type: new
Abstract: The advent of tool-using LLM agents shifts safety monitoring from output moderation to auditing long, noisy interaction trajectories, where risk-critical evidence is sparse-making standard binary supervision poorly suited for credit assignment. To add...
arXiv:2604.03240v1 Announce Type: new
Abstract: Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding generation in external knowledge, yielding relevance responses that are aligned with factual evidence and evolving corpora. Standard RAG pipelines construct contex...
LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task Learning
arXiv:2604.02338v1 Announce Type: new
Abstract: MoE-PEFT methods combine Mixture of Experts with parameter-efficient fine-tuning for multi-task adaptation, but require separate adapters per expert causing trainable parameters to scale linearly with expert count and limiting applicability to adapter...
Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models
arXiv:2604.02340v1 Announce Type: new
Abstract: Recent advances in masked diffusion language models (MDLMs) narrow the quality gap to autoregressive LMs, but their sampling remains expensive because generation requires many full-sequence denoising passes with a large Transformer and, unlike autoreg...