Daily Radar — 2026-07-05

Window: July 3–5 2026 (arXiv 2607.xxxxx primary); extended to uncovered June–May 2026 preprints not surfaced in prior daily sweeps · Sources swept: ICML 2026 Mech Interp Workshop, arXiv (cs.CL/cs.LG/cs.CR/cs.AI), LessWrong/Alignment Forum, Google DeepMind blog Counts: 0 peer-reviewed · 2 preprints · 0 forum/blog

Top 2 (priority order)

1. Machine Unlearning for Masked Diffusion Language Models

• Authors / venue: (authors at submission) — arXiv preprint (cs.CL/cs.LG), May 2026
• Why it ranks here: First unlearning framework specifically designed for MDLMs (LLaDA, Dream), bridging the machine-unlearning/concept-erasure research agenda to the fastest-growing LLM architecture class. Particularly high priority given the combination of dLLM + unlearning/security scope.
• Technical summary: Unlike autoregressive LLMs, MDLMs generate text by iteratively denoising masked positions in parallel — a fundamentally different generative and fine-tuning mechanism that existing LLM unlearning methods don’t accommodate. MDU (Masked Diffusion Unlearning) revisits how specific knowledge is learned in terms of the diffusion process and minimizes a forward KL divergence from the prompt-conditional prediction to a prompt-masked unconditional anchor at every masked response position, with a temperature scaling parameter that controls the privacy-utility trade-off. This formulation is architecture-native: it operates on the forward masking process rather than on output logits, making it directly compatible with MDLM fine-tuning. Empirical results on standard benchmarks across multiple MDLM backbones show MDU achieves high unlearning performance while outperforming existing LLM unlearning methods adapted for MDLMs. Code at github.com/leegeoru/MDU.

02. Toward Identifiable Sparse Autoencoders

• Authors / venue: Walter Nelson, Theofanis Karaletsos, Francesco Locatello — arXiv preprint (cs.LG), May 2026
• Why it ranks here: Provides a theoretically grounded iSAE variant with proven near-identifiability conditions and lower reconstruction error than standard TopK SAEs — directly addresses whether SAE features represent stable, ground-truth model properties or training artifacts.
• Technical summary: Standard SAEs are highly unstable: different training runs produce different concept dictionaries and sparse codes, making it unclear whether SAE features reflect genuine model structure or optimization accidents. The paper characterizes the model properties that hinder real-world SAE stability and addresses each through minimal architectural and training changes, yielding iSAE (identifiable SAE) — a TopK SAE variant with lower reconstruction error and improved cross-run feature stability. The authors explain this improvement theoretically by connecting SAEs to classical dictionary learning: they show that dictionaries learned in practice satisfy an approximate restricted isometry condition (RIC), and that satisfying RIC renders the corresponding sparse codes near-identifiable — i.e., approximately unique. Two iSAE variants are derived from different stability-inducing constraints, each with a distinct theoretical guarantee regime.

Notes

Written before the repeat cleanup of 2026-09-10; may refer to entries listed under ‘Removed repeats’ below.

• ICML 2026 Mech Interp Workshop (July 10, Seoul): D2D (#1) is confirmed accepted; the full accepted-poster list (including 23 spotlights) is now online at mechinterpworkshop.com. Expect further 2607.xxxxx workshop paper postings through July 9.
• dLLM cluster: #2 (DiffusionGemma transparency), #4 (MaskForge attack), #5 (Steering Without Breaking), and #6 (MDU unlearning) form a dense cluster on the text-diffusion-model agenda — all four sit at the intersection of the primary focus areas. Flag for weekly roundup synthesis.
• SAE methodology cluster: #3 (SASA / feature splitting fix), #8 (seed dependence / subspace reproducibility), and #10 (iSAE / identifiability) address different aspects of the SAE reliability problem. Together they represent a week of sustained theoretical progress on SAE foundations — recommend weekly synthesis covering all three alongside yesterday’s Geometric View (#5, July 4 report).
• Mech interp for coding-agent safety (#7, AgentLens): Paired with Steerability via Constraints (#8, July 4 report), this forms an emerging cluster applying circuit/subspace methods to runtime agent safety. Track for weekly roundup.
• Stealth-bias detection (#1): D2D is notable for detecting invisible supply-chain tampering via soft logit distributions rather than outputs — relevant to the AI control and model security agenda beyond the mech-interp framing of the workshop submission.

Removed repeats

8 entries removed on 2026-09-10 because the paper had already been covered by an earlier report:

• 2607.01208 — Distill to Detect: Exposing Stealth Biases in LLMs through Cartridge Distillation (first covered 2026-07-03)
• 2606.20560 — How Transparent is DiffusionGemma? (first covered 2026-07-01)
• 2606.06333 — Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability (first covered 2026-07-02)
• 2606.04027 — MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models (first covered 2026-07-02)
• 2605.10971 — Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models (first covered 2026-07-01)
• 2606.22673 — AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent (first covered 2026-07-02)
• 2606.12138 — Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders (first covered 2026-07-02)
• 2606.24026 — Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability? (first covered 2026-07-02)