Direct Pass@$k$ Optimization for Thought Pruning: Balancing Quality and Diversity in Test-Time Reasoning
Test-time scaling has emerged as a key inference strategy for reasoning models, where a model generates a large number of…
News
Research & Science
Papers, breakthroughs and what the labs found this week.
588 stories · Every headline links to the original publisher. HapnGo curates and groups; we do not copy articles.
Phase Transition from Random Features to Fully Trainable Networks
Constructing accurate and computationally tractable approximation spaces is a fundamental task in scientific computing. Partially…
Reliable AI-Assisted Decisions via Selective Auditing
We consider online monitoring of an AI system that produces a sequence of decisions. At each round, the system outputs a proposed…
SpectralCanary: Embarrassingly Simple Low-Frequency Traces for T2I Dataset-Use Auditing
Auditing whether a text-to-image (T2I) model was fine-tuned on a particular image collection is difficult: a model can absorb…
Cost-Aware Abstention for LLM-Based IT Ticket Classification
Wrong automatic routing of an IT support ticket can cost more than human triage. We evaluate cost-aware abstention as an offline…
METTA: Memory-Enhanced Test-Time Adaptation for Meta-Reinforcement Learning
Meta-reinforcement learning aims to train agents that adapt quickly to unseen tasks from limited interaction, but this requires…
Low-Bit N-Gram Embeddings for Language Models
Many recent open-weight language models use n-gram embedding tables to improve performance. These tables store learned…
Causal Chain of Thought: Mitigating Attention Leakage via Context Isolation
Chain-of-thought (CoT) prompting elicits step-by-step rationales that appear to explain model predictions, but there is no…
Questioning Instrumental Convergence in RLVR: Checkpoint Evidence from OLMo-3
Instrumental convergence is often invoked as a general reason to expect capable agents to acquire or express power-seeking…
Flint-interactive: A language for creating interactive data visualizations
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight…
Recursive shows first result of its AI-driven research process with Flint
The AI startup Recursive is unveiling Flint, its first language model, a 40-billion-parameter MoE for local coding developed by…
Meet Mori, a Cute Robot Mushroom That Doesn’t Really Say (or Do) Anything
Step one in convincing people to live with robots with cameras on their faces? Disguise them as cute home decor.
Different Tasks, Different Timesteps: Temporal Task-Aware Quantization for Diffusion Language Models
Diffusion Language Models (DLMs) introduce unique quantization challenges due to their iterative denoising process. In this work…
Inside-JEPA: From Prediction to Relational Grounding in Latent World Models
Joint-embedding predictive architectures (JEPAs) learn world models in latent space, enabling efficient planning but leaving…
RaSFNet: Ray-aligned and Scan-aware Fusion Network for LiDAR Semantic Segmentation
LiDAR point cloud semantic segmentation is a fundamental component of 3D perception for autonomous driving and robotics…
Prompting Strategy Effects Depend on the Judge: A Multilingual Study of LLM-as-a-Judge Robustness
LLM-as-a-Judge evaluation is increasingly applied to multilingual tasks, yet prompting strategies such as Chain-of-Thought and…
Memory before Goal: Role of Pre-History Memory for Humanoid Loco-Manipulation
Humanoid loco-manipulation in dynamic scenes is non-Markovian: cues vanish as objects change or are hidden, or leave the view as…
Network topology shapes consensus and vulnerability in LLM populations
As large language models (LLMs) are deployed in interacting populations, their collective behaviour depends not only on the…
Prompt Sensitivity in Tool-Augmented Model Comparisons
Language models are compared on question-answering benchmarks that pose each question in one wording, and a reworded question can…
PriMa-Causa: Causal Prescriptive Maintenance
Automated manufacturing requires data-driven decisions under uncertainty and sparse observational records, and unplanned downtime…
Rethinking Fisher Vectors for Second-order Multi-scale Deep Feature Aggregation in Scalable Scene Retrieval
Aggregating CNN responses into a compact discriminative vector, given their lack of geometric invariance, is a challenge. To…
Mixing Matters: Evidence Position Bias Across Sequence Mixers in Long-Context Question Answering
Long-context models often use answer-bearing evidence less effectively when it appears away from a prompt boundary. We compare…
Google Explains The Limit Of Robots.txt For AI Content Use
Google's new robots.txt video says the standard covers crawling, not how content gets used, and recommends percent-encoding…
Free, daily
The HapnGo Briefing, in your inbox
One email a day with the AI stories that matter, why they matter, and one tool worth trying. No spam, one-click unsubscribe.