·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Faithful, Not Corrective: Message-Format Effects in Multi-Hop Agent Relays Are Tier-Dependent5h◆A Dynamic Scene Interaction Reasoning Framework for Scene-level Lane-Change Intention and Trajectory Prediction of Multiple Interacting Vehicles5h◆LegalFarePlan: A Label-Setting Framework for Fare-Transparent Urban Rail Route Planning under Non-Additive Fare Rules5h◆First-Order Modal Logic in HOL: Deep and Shallow Embeddings with Automated Faithfulness (Extended Preprint)5h◆SETA: Scaling Environments for Terminal Agents5h◆Incremental Transformer for Surrogate-Based Inverse Design of Geopolymer Mixtures5h◆Learning Linear Temporal Specifications from Demonstrations with Uncertainty5h◆STAMP: Provenance-Guided Credit Assignment for Deep Search Agents5h◆The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy5h◆SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL5h◆What We Talk About When We Talk About LLM Planning: Evidence for Two Distinct Planning Abilities5h◆PREF-Gate: Provenance-Constrained Relational Evidence Fusion with Validation-Gated Selection for Graph Fraud Detection5h◆Heterogeneous Agent Cohorts for Safe Open-Ended Exploration with Runtime Constraint Memory5h◆Bringing Back Rule Induction to Fluid Intelligence Research? An Initial Validation of the ARC-AGI Benchmark in Humans5h◆Valid $\ne$ Necessary: Diagnosing Latent Inefficiency in Chain-of-Thought5h◆Efficient Test-Time Optimization for Multi-Agent Proof Autoformalization5h◆Calibrated e-CUSUM Decoding for Quantized Reasoning Models: Why Token Log-Probability Is the Wrong Observable for Decoding Monitors5h◆Verifier-Guided Twelve-Tone Composition: A Generate-Verify-Repair Harness for Symbolic Music Generation5h◆AutoVSR: Automatic Visual-to-Symbolic Reasoning for Symbolic Expression Generation from Circuit Schematic5h◆Compile, Then Page: Executable SOP Programs and a Capability-Gated Runtime for Procedural LLM Agents5h◆Faithful, Not Corrective: Message-Format Effects in Multi-Hop Agent Relays Are Tier-Dependent5h◆A Dynamic Scene Interaction Reasoning Framework for Scene-level Lane-Change Intention and Trajectory Prediction of Multiple Interacting Vehicles5h◆LegalFarePlan: A Label-Setting Framework for Fare-Transparent Urban Rail Route Planning under Non-Additive Fare Rules5h◆First-Order Modal Logic in HOL: Deep and Shallow Embeddings with Automated Faithfulness (Extended Preprint)5h◆SETA: Scaling Environments for Terminal Agents5h◆Incremental Transformer for Surrogate-Based Inverse Design of Geopolymer Mixtures5h◆Learning Linear Temporal Specifications from Demonstrations with Uncertainty5h◆STAMP: Provenance-Guided Credit Assignment for Deep Search Agents5h◆The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy5h◆SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL5h◆What We Talk About When We Talk About LLM Planning: Evidence for Two Distinct Planning Abilities5h◆PREF-Gate: Provenance-Constrained Relational Evidence Fusion with Validation-Gated Selection for Graph Fraud Detection5h◆Heterogeneous Agent Cohorts for Safe Open-Ended Exploration with Runtime Constraint Memory5h◆Bringing Back Rule Induction to Fluid Intelligence Research? An Initial Validation of the ARC-AGI Benchmark in Humans5h◆Valid $\ne$ Necessary: Diagnosing Latent Inefficiency in Chain-of-Thought5h◆Efficient Test-Time Optimization for Multi-Agent Proof Autoformalization5h◆Calibrated e-CUSUM Decoding for Quantized Reasoning Models: Why Token Log-Probability Is the Wrong Observable for Decoding Monitors5h◆Verifier-Guided Twelve-Tone Composition: A Generate-Verify-Repair Harness for Symbolic Music Generation5h◆AutoVSR: Automatic Visual-to-Symbolic Reasoning for Symbolic Expression Generation from Circuit Schematic5h◆Compile, Then Page: Executable SOP Programs and a Capability-Gated Runtime for Procedural LLM Agents5h◆
News/HeRo-Q: A General Framework for Stable Low Bit Quantization via Hessian Conditioning
arxiv
PublishedJune 18, 2026 at 4:00 AM
—neutral

HeRo-Q: A General Framework for Stable Low Bit Quantization via Hessian Conditioning

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2601.21626v2 Announce Type: replace-cross Abstract: Post Training Quantization (PTQ), a mainstream model compression technique, often leads to the paradoxical 'low error, high loss' phenomenon because it focuses solely on minimizing quantization error. The root cause lies in the Hessian matrix

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivFaithful, Not Corrective: Message-Format Effects in Multi-Hop Agent Relays Are Tier-Dependent5harxivA Dynamic Scene Interaction Reasoning Framework for Scene-level Lane-Change Intention and Trajectory Prediction of Multiple Interacting Vehicles5harxivLegalFarePlan: A Label-Setting Framework for Fare-Transparent Urban Rail Route Planning under Non-Additive Fare Rules5harxivFirst-Order Modal Logic in HOL: Deep and Shallow Embeddings with Automated Faithfulness (Extended Preprint)5h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews