Records published in April 2026
11 records, all free to read and download.
All of 2026-
Journal article
Energy-Based Models for Reasoning: A Critical Assessment of Theoretical Advantages and a Research Agenda
Modern reasoning systems are dominated by autoregressive models trained with reinforcement learning on reasoning trajectories — the o1, R1, and Claude 3.7 family of "thinking" models. Energy-based models (EBMs) offer a theoretically appealing alternative: they model joint distributions…
-
Journal article
AI-Generated Text Detection Under Paraphrasing: What Has Been Solved, What Has Not, and Why Bias Matters
The detection of AI-generated text under adversarial transformation — particularly paraphrasing — is widely characterised as an unsolved problem. The reality is more structured. Two technically distinct approaches, post-hoc detection and watermarking, are routinely conflated in policy…
-
Journal article
Formal Verification of Neural Network Safety Beyond Toy Examples: Three Distinct Gaps and a Specification-First Research Agenda
Formal verification of neural networks has matured into a real research area. Tools such as alpha-beta-CROWN, ERAN, and Marabou now reliably verify L-infinity robustness properties of ReLU networks at the ResNet scale, with the annual VNNCOMP competition documenting steady year-over-year…
-
Journal article
Mechanistic Interpretability of In-Context Learning: A Survey of Known Circuits and Open Problems
In-context learning (ICL) — the ability of a transformer language model to acquire a new input-output mapping from a handful of demonstrations in its prompt, with no weight updates — remains the most striking and least understood capability of large language models. Mechanistic…
-
Journal article
Cross-Lingual Hallucination Patterns in Indic Languages: A Typology-Aware Research Agenda for Dravidian and Indo-Aryan Comparison
Multilingual hallucination in large language models has begun to receive systematic attention. Recent work has measured aggregate hallucination rates across 19 to 30 languages (FACTSCORE-multilingual, MFAVA, Poly-FEVER), introduced multilingual benchmarks (HalluVerseM3, BHRAM-IL for some…
-
Journal article
Causal Representation Learning from Observational Video: Identifiability Assumptions and the Gap Between Synthetic and Real-World Settings
Causal representation learning (CRL) — the recovery of latent causal variables and their causal graph from high-dimensional observations — has produced a substantial body of theoretical results in the past five years. CITRIS, CauCA, CRID, mechanismsparsity methods, and the recent…
-
Journal article
Catastrophic Forgetting in Continual RLHF: A Measurement Framework for Round-Over-Round Capability Degradation
Reinforcement learning from human feedback (RLHF) is widely understood to incur an alignment tax: aligning a language model with human preferences can degrade capabilities the base model possessed. This phenomenon is well documented in single-round comparisons. What is not well…
-
Journal article
Memory Architectures Beyond Attention: Disambiguating Four Memory Concepts and the Long-Context Reasoning Frontier
State-space models did not merely "open a door" beyond attention; they walked through it. Mamba, Mamba-2, Samba, Jamba, Granite 4, Hymba, and a growing family of hybrid attention-SSM architectures are now in production language models, demonstrating that linear-time alternatives to…
-
Journal article
Neuromorphic Computing for On-Device LLM Inference: Why the Three-Layer Integration Gap Matters More Than the Algorithm Layer
Spiking neural networks (SNNs) on neuromorphic hardware are routinely proposed as the path to energy-efficient on-device inference for language models. The framing usually treats this as a single technical question. It is not. There are three distinct technical layers — SNN algorithms…
-
Journal article
Beyond ASL: AI for Low-Resource Sign Languages A Research Agenda for Indian and African Contexts
There are over 300 sign languages in active use worldwide, serving an estimated 70 million Deaf signers. Despite this, the overwhelming majority of AI research on sign languages targets American Sign Language (ASL), with smaller but growing efforts on German, British, Chinese, and Indian…
-
Journal article
Emergent Covert Signaling in Multi-Agent LLM Negotiation: A Conceptual Framework and Experimental Protocol
When multiple large-language-model agents negotiate, communicate, or compete, do they spontaneously develop covert signalling — channels of communication that human observers cannot decode? Recent work has established that such behaviour is possible: LLMs can be trained or pressured into…