CircuitProbe: Predicting Reasoning Circuits in Transformers via Stability Zone Detection
arXiv:2604.00716v1 Announce Type: new Abstract: Transformer language models contain localized reasoning circuits, contiguous layer blocks that improve reasoning when duplicated at inference time. Finding these circuits currently requires brute-force sweeps costing 25 GPU hours per model. We propose CircuitProbe, which...
Beyond Symbolic Solving: Multi Chain-of-Thought Voting for Geometric Reasoning in Large Language Models
arXiv:2604.00890v1 Announce Type: new Abstract: Geometric Problem Solving (GPS) remains at the heart of enhancing mathematical reasoning in large language models because it requires the combination of diagrammatic understanding, symbolic manipulation and logical inference. In existing literature, researchers have chiefly...
Coupled Query-Key Dynamics for Attention
arXiv:2604.01683v1 Announce Type: new Abstract: Standard scaled dot-product attention computes scores from static, independent projections of the input. We show that evolving queries and keys \emph{jointly} through shared learned dynamics before scoring - which we call \textbf{coupled QK dynamics} -...
Polish phonology and morphology through the lens of distributional semantics
arXiv:2604.00174v1 Announce Type: new Abstract: This study investigates the relationship between the phonological and morphological structure of Polish words and their meanings using Distributional Semantics. In the present analysis, we ask whether there is a relationship between the form properties...
Cognitive Energy Modeling for Neuroadaptive Human-Machine Systems using EEG and WGAN-GP
arXiv:2604.01653v1 Announce Type: new Abstract: Electroencephalography (EEG) provides a non-invasive insight into the brain's cognitive and emotional dynamics. However, modeling how these states evolve in real time and quantifying the energy required for such transitions remains a major challenge. The...
15% of Americans say they’d be willing to work for an AI boss, according to new poll
According to a Quinnipiac University poll, 15% of Americans say they'd be willing to have a job where their direct supervisor was an AI program that assigned tasks and set schedules.
DDCL: Deep Dual Competitive Learning: A Differentiable End-to-End Framework for Unsupervised Prototype-Based Representation Learning
arXiv:2604.01740v1 Announce Type: new Abstract: A persistent structural weakness in deep clustering is the disconnect between feature learning and cluster assignment. Most architectures invoke an external clustering step, typically k-means, to produce pseudo-labels that guide training, preventing the backbone from...
MiCA Learns More Knowledge Than LoRA and Full Fine-Tuning
arXiv:2604.01694v1 Announce Type: new Abstract: Minor Component Adaptation (MiCA) is a novel parameter-efficient fine-tuning method for large language models that focuses on adapting underutilized subspaces of model representations. Unlike conventional methods such as Low-Rank Adaptation (LoRA), which target dominant subspaces,...
In harmony with gpt-oss
arXiv:2604.00362v1 Announce Type: new Abstract: No one has independently reproduced OpenAI's published scores for gpt-oss-20b with tools, because the original paper discloses neither the tools nor the agent harness. We reverse-engineered the model's in-distribution tools: when prompted without tool definitions,...
Improvisational Games as a Benchmark for Social Intelligence of AI Agents: The Case of Connections
arXiv:2604.00284v1 Announce Type: new Abstract: We formally introduce a improvisational wordplay game called Connections to explore reasoning capabilities of AI agents. Playing Connections combines skills in knowledge retrieval, summarization and awareness of cognitive states of other agents. We show how...
Robust Graph Representation Learning via Adaptive Spectral Contrast
arXiv:2604.01878v1 Announce Type: new Abstract: Spectral graph contrastive learning has emerged as a unified paradigm for handling both homophilic and heterophilic graphs by leveraging high-frequency components. However, we identify a fundamental spectral dilemma: while high-frequency signals are indispensable for encoding...
English to Central Kurdish Speech Translation: Corpus Creation, Evaluation, and Orthographic Standardization
arXiv:2604.00613v1 Announce Type: new Abstract: We present KUTED, a speech-to-text translation (S2TT) dataset for Central Kurdish, derived from TED and TEDx talks. The corpus comprises 91,000 sentence pairs, including 170 hours of English audio, 1.65 million English tokens, and 1.40...
How Do Language Models Process Ethical Instructions? Deliberation, Consistency, and Other-Recognition Across Four Models
arXiv:2604.00021v1 Announce Type: cross Abstract: Alignment safety research assumes that ethical instructions improve model behavior, but how language models internally process such instructions remains unknown. We conducted over 600 multi-agent simulations across four models (Llama 3.3 70B, GPT-4o mini, Qwen3-Next-80B-A3B,...
Culturally contextual datasheets: a framework for embedding cultural reflexivity in global AI governance
No Third Term: Rejecting the Nonconsecutive Loophole – Wisconsin Law Review – UW–Madison
The text of the Twenty-Second Amendment seems clear that a president cannot be elected to a third term: “No person shall be elected to the office of the President more than twice.” This Essay looks further to the history surrounding...
Natural language processing for legal document review: categorising deontic modalities in contracts
RAG-Based Local Law Navigator: An AI-Powered Legal Assistance System
Court to hear argument on claim of racial discrimination in jury selection
The Supreme Court will hear oral argument on Tuesday in Pitchford v. Cain, the case of a Mississippi man who contends that he was sentenced to death in violation of […]The postCourt to hear argument on claim of racial discrimination...
Brady violations, child abduction, qualified immunity, and confessions of error
The Relist Watch column examines cert petitions that the Supreme Court has “relisted” for its upcoming conference. A short explanation of relists is available here. This week, the Supreme Court started […]The postBrady violations, child abduction, qualified immunity, and confessions...
Prominent Scientists, Faith Leaders, Policymakers and Artists Call for a Prohibition on Superintelligence, as Poll Shows Americans Don’t Want It
Initial signatories include AI pioneers Yoshua Bengio and Geoffrey Hinton, leading media voices Steve Bannon and Glenn Beck, Obama's National Security Advisor Susan Rice, business trailblazers Steve Wozniak and Richard Branson, five Nobel Laureates, former Irish President Mary Robinson, actors...
Statement: Head of US Policy on the White House AI legislative recommendations
The White House published it’s long-awaited AI legislative recommendations on Friday, and it still includes a call for Congress to […]
“This is What it Means to be Pro-Human” Declares Broad Coalition of Conservative, Progressive, and Civil Society Groups in Statement of Shared Principles on AI
Amid a rising backlash to Silicon Valley overreach, a remarkably diverse group from across the political spectrum announced a set of AI principles to clearly define the goals of the emerging pro-human movement.
Future of Life Institute Launches Multimillion Dollar Nationwide AI Regulation Campaign
The Protect What’s Human campaign will push for commonsense AI safety rules at federal and state level
AI Company Safety Practices Fall Short of Public Commitments and Show Structural Weaknesses, as Top Performers Widen the Gap
But in a win for transparency, five leading companies participated in the scorecard's survey for the first time, providing critical new information to the public.
Google DeepMind Falls Behind OpenAI in Latest Safety Review; All AI Companies Still Falling Short, Say Experts
The Future of Life Institute’s 2025 summer update to its AI Safety Index shows some companies making incremental progress, but dangerous gaps remain in key categories such as risk assessment and controlling the systems they plan to build.
DOJ confirms FBI Director Kash Patel’s personal email was hacked
Hackers claimed the attack was retaliation after Patel vowed to "hunt" them.
Senators want US energy information agency to monitor data center electricity usage
In a letter, senators press for mandated annual electricity disclosure for data centers.
Bluesky leans into AI with Attie, an app for building custom feeds
Bluesky’s new app Attie uses AI to help people build custom feeds the open social networking protocol atproto.
Stanford study outlines dangers of asking AI chatbots for personal advice
While there’s been plenty of debate about AI sycophancy, a new study by Stanford computer scientists attempts to measure how harmful that tendency might be.
Elon Musk’s last co-founder reportedly leaves xAI
All but two of Musk's 11 xAI co-founders departed before this week.