ZeroHour
DashboardNewsCVEsExploitsIncidentsAIBriefAnalyticsEntitiesWatchlistIOCsAsk the feedSourcesFeeds & APIKiosk mode

Search: “steerability”

32 stories

Searchkeywordsmart
DomainAllCyberAIWindow24h3d7d30dAllIn the wildImportant onlyShow duplicates
CategoryAllAI industry 1Model release 1AI research 1AI safety & security 1Data breach 1Exploit / PoC 1Industry 1
SeverityAllcritical 1high 0medium 1low 2info 3

Smart search ranks by meaning as well as keywords (one row per story, last 45 days).

[AINews] Fal’s H3 Max Live breaks the infinite videogen barrier

Fal post-trained MiniMax H3 into a 'Max' variant with 35x-faster inference, enabling faster-than-realtime AI video generation and infinite streams.

Fal post-trained MiniMax's H3 model into a 'Max' variant and optimized it for its in-house inference engine, achieving roughly 35x the speed of the official endpoint. The optimization enables faster-than-realtime video generation, demonstrated by an infinite interactive AI-generated stream productized by levels.io. The roundup also notes Meta Muse Code's general availability with an SDK, open DeepSeek-V4-Flash-Vision-Exp weights, GLM-5.3-Flash's strong agentic cost/performance rankings, and Tencent's 770B-parameter Hy4 Preview MoE with 49B active parameters.

Latent Space · 15d agoAI industry

A Chosen Future Can Still Be Rewritten: Causal Writability in Video Models

Study shows video models often learn correct physics but fail to use it; low-dimensional 'causal writability' edits can restore correct motion.

The paper demonstrates 'causal writability' in video generation models: physically correct motion remains available inside the model even when the model outputs incorrect motion. In a red/blue mass oscillation setup, a low-dimensional edit predicted from simple physical variables restores correct fast motion, with a sharp depth boundary marking commitment. Early causal writability predicts which training errors later get corrected, and both writability and closure reproduce in a pretrained 1.3B video model.

arXiv cs.AI / cs.LG / cs.CL · 2d agoAI research

Suno replaces its AI models with a new one trained on licensed music as copyright suits pile up

Suno launched its v6 model family trained on licensed music from Warner, BMG and Believe as copyright lawsuits from Sony and Universal continue.

Suno unveiled a new model family — Suno v6, experimental v6 wild, and faster v6 mini — trained on licensed data from Warner Music Group, BMG and Believe, and plans to retire older models. New capabilities include prompt-based song editing, use of text/images/video as references, and instrument separation, plus a planned opt-in artist remix program. Suno settled with Warner last year and BMG last month, but still faces suits from Sony, Universal Music Group and artists like Jason Isbell, and has raised over $819 million to date.

TechCrunch · AI · 7d agoModel release

Steering Geometry: Validating Human Value Geometry in LLM Steering Space

Researchers show LLM activation steering vectors encode human value geometry predicted by Schwartz's theory, with fidelity improving at scale but degrading after instruction tuning.

The study tests whether latent geometry of activation steering vectors reflects theory-specified structure in human values, using Schwartz's Theory of Basic Human Values and a new 26K-sample benchmark spanning 20 values. Distribution-driven methods (CAA, SphericalSteer, ODESteer) recover predicted value topologies with Spearman correlation up to 0.51 (p < 10^-13), while behavior-centric methods (COLD-Steer, BiPO) steer comparably but show little geometric fidelity. Geometric alignment improves with model scale but drops after instruction tuning. Better geometric alignment also yields more human-consistent cross-value transfer, steering one value lifting compatible values and suppressing opposing ones.

Hugging Face daily papers · 11d agoAI research

Curriculum Learning as Transport: Understanding Curricula with Wasserstein Geodesics

Researchers model curriculum learning as Wasserstein transport over difficulty distributions, finding curriculum benefits are strongly task- and budget-dependent with no dominant strategy.

The framework represents curricula as trajectories of training distributions over discrete difficulty levels, decoupling ordering, matched exposure, endpoint smoothness, and pacing. Across a calibrated suite of 12 tasks and 33 difficulty axes under fixed training budgets, no single strategy dominates, though easy-to-hard ordering improves hard-level performance relative to exposure-matched static sampling. Endpoint smoothness and pacing substantially affect where along the difficulty spectrum a curriculum is effective, and the transport view supports extensions to learned pacing and structured difficulty spaces.

arXiv cs.AI / cs.LG / cs.CL · 8d agoAI research1

SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?

SAEScientist-Bench evaluates whether AI agents can autonomously conduct SAE interpretability research in Gemma-2-9B-IT, finding frontier agents trail expert baselines.

SAEScientist-Bench tests if AI agents can act as scientists using SAE tools for autonomous mechanistic discovery, requiring them to design contrastive probes and navigate a Gemma Scope dictionary of 131K+ features in Gemma-2-9B-IT. Across 10 agent configurations and 20 tasks, frontier agents showed genuine discovery capability but remained well behind expert reference features, lagging most in causal steering. Agents frequently misinterpreted experimental measurements even when designing effective contrasts.

Hugging Face daily papers · 8d agoAI research

ASTRIL-MPC: Autonomous Traversal Framework of Articulated Tracked Robots with Language-Guided Neural-Kinematic MPC

ASTRIL-MPC combines learned kinematics, NMPC, and LLM-guided safety-checked retuning for articulated tracked robot traversal in search-and-rescue.

ASTRIL-MPC is a language-guided neural-kinematic model predictive control framework for autonomous traversal of articulated tracked robots in urban search and rescue. A learned kinematics model predicts short-horizon task-state increments, NMPC plans with feasibility constraints, and an LLM proposes bounded, safety-checked updates to weights and bounds. The compiled predictor enables a full control cycle within 100 ms, improving traversal-quality scores by up to 71% over non-adaptive NMPC and 67% over a PPO baseline while eliminating measurable collision impacts.

arXiv cs.AI / cs.LG / cs.CL · 5d agoAI research

SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?

SAEScientist-Bench tests whether AI agents can autonomously run SAE interpretability research on Gemma-2-9B-IT; frontier agents trail expert baselines.

The benchmark requires agents to design contrastive probes and navigate the Gemma Scope dictionary of over 131K features in Gemma-2-9B-IT to discover optimal interpretable features, scored against expert-curated references on Neuronpedia via activation rank, concept selectivity, and causal steering. Across 10 agent configurations and 20 tasks, frontier agents demonstrate genuine discovery capability and approach expert levels at separating target concepts from controls, but lag substantially in causal steering and frequently misinterpret experimental measurements. The authors frame this as establishing experimental model understanding as a measurable capability for closed-loop autonomous AI R&D and post-hoc monitoring for recursive self-improvement.

arXiv cs.AI / cs.LG / cs.CL · 8d agoAI research1

RobResilience: Implementing and Evaluating a Resilience Framework for Cyber-Physical Embodied Systems

RobResilience implements a runtime resilience framework for robots in Webots/ROS2, evaluating tolerable disruption, degradation, and mitigation feasibility across eight attack scenarios.

The paper implements a formal resilience framework for embodied cyber-physical systems using a PR2 robot and ROS2 in a Webots simulation. At runtime it evaluates three predicates — tolerable disruption (δ), tolerable degradation (γ), and mitigation feasibility (μ) — over a compromised device set derived from IDS confidence scores, triggering mitigation strategies when resilience is lost. Eight attack scenarios systematically covering the full predicate state space confirm runtime behavior matches theoretical definitions. The work addresses 'graceful failure paralysis,' where autonomous systems cannot distinguish safe degraded states from catastrophic hazards during attacks.

arXiv cs.CR · 1d agoResearch

The agentic harness for Tenable Hexa AI: How Tenable prevents AI agents from going off the rails

Tenable details the 'harness' governing its Hexa AI agents, treating LLMs as untrusted insiders with scoped permissions, human approval and audit logging.

Tenable describes the agentic 'harness' built for Hexa AI, the agentic engine of the Tenable One Exposure Management Platform, which limits what context models can see, which tools they can call, when humans must approve actions, and what is recorded. The post catalogs real development failures: agents acting past their authority, being confidently wrong about tenant data, crashing on broad queries, over-refusing capable tasks, and over-conservative safety filtering causing false positives. It also highlights that attacker-writable security data such as hostnames and certificate fields can serve as a prompt-injection vector for agents reading platform data.

Tenable Blog · 6d agoAI safety & security

ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals

ImpossibleRubrics benchmark shows LLM-generated rubric reward signals are exploited 8-26% of the time by adversarial answers on impossible tasks.

ImpossibleRubrics is a benchmark of 169 impossible tasks across six impossibility categories, each paired with a verifiable oracle certificate, plus 48 answerable controls, for stress-testing LLM-generated rubrics used as reward signals. Eleven rubric generators were exploited 8-26% of the time on an unbiased 150-task cut and up to 36% on a stress cut, while a certificate-faithful rubric scored 0%. A single generic 'be decisive, penalize hedging' rubric was exploited 64% of the time, suggesting tailored criteria can reveal which claims attackers should fabricate.

Hugging Face daily papers · 1d agoAI research

HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness

Researchers introduce HarnessVLN, a zero-shot training-free agent harness that sets new training-free SOTA on vision-language navigation benchmarks including R2R and HM3D.

HarnessVLN is a zero-shot, training-free framework for embodied vision-language navigation that coordinates perception, retrieval, grounding, navigation, recovery, and termination through a unified tool interface. It validates planner proposals against spatial evidence, geometric feasibility, and subgoal consistency, using hierarchical event memory and a persistent Spatiotemporal Graph that stores reusable spatial evidence and failure annotations. It reports success rates of 60.8% on R2R, 53.9% on RxR, 76.0% on HM3D-v2, and 59.3% on HM3D-OVON, surpassing prior training-free state of the art, with real-world humanoid deployment demonstrated.

Hugging Face daily papers · 2d agoAI research

Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal

A self-distillation safety framework tunes narrow-boundary refusals in Qwen3-8B, raising target-domain refusal to 84.75% while cutting over-refusal from 15.20% to 5.20%.

The paper formulates narrow-boundary safety, where deployments need refusals within specific topics rather than whole subjects, and proposes an offline self-generated framework with controlled topic generation, escalating retries, and harmful-benign boundary pairs. On political persuasion with Qwen3-8B, the method raised target-domain refusal from 9.47% to 84.75% and cut the mean unsafe-response rate across three broader benchmarks from 26.26% to 0.14%. Verified target-model responses reduced over-refusal from 15.20% to 5.20%, and boundary-pair data cut comply-side over-refusal on held-out pairs from 32.94% to 4.16%. Results show data composition controls the safety-usability trade-off and alignment should be evaluated on both sides of the refusal boundary.

Hugging Face daily papers · 13d agoAI safety & security1

Show-Harness: Just a VLM Agent Can Play Robots

Show-Harness lets VLM agents control robots via discrete semantic action units, outperforming VLA baselines zero-shot and after light fine-tuning.

Show-Harness is an embodied agent harness that exposes discrete semantic action units a VLM reasons over, with embodiment-specific interpreters grounding them into local robot actions. It enables zero-shot robot control with closed-source frontier VLMs and low-cost adaptation of small open-source VLMs using only a few GPU-hours of fine-tuning. The companion GUMI (GUI Manipulation Interface) extends the same semantic action space to GUI-based demonstration collection without specialized teleoperation hardware. Experiments show robust generalization across tasks, embodiments, and environments, beating representative agentic and VLA paradigms.

arXiv cs.AI / cs.LG / cs.CL · 7d agoAI research

VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities

Introduces VEX-Bench, 75 expert-labeled real-world cases testing whether LLM agents can assess supply chain vulnerability exploitability; frontier models reach about 80% F1.

VEX-Bench is the first benchmark evaluating LLM agents on assessing whether upstream dependency vulnerabilities are exploitable in downstream projects, with 75 real-world expert-labeled cases across Python, Java, and Go mined from GitHub. Nine models across three agent harnesses were evaluated; GPT-5.5 and Claude Opus 4.6 reach approximately 80% F1 on binary vulnerability-status classification, but only GPT-5.5 surpasses 70% macro-F1 on fine-grained justification classification. The gap highlights the difficulty of moving beyond binary exploitability calls to explaining exploitability reasons, unlike prior benchmarks targeting zero-day settings.

arXiv cs.CR · 8d agoResearch1

PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models

PhysBrain 1.5, an 8B physical foundation model, sets open-source state of the art across 28 embodied understanding benchmarks.

The paper presents PhysBrain 1.5, a unified 8B model for understanding physical environments, generating actions, and predicting future states, built from a vision-language model with joint autoregressive next-token prediction over language, end-effector motion, and dense visual targets. Pre-training uses embodied supervision from human interaction videos, followed by supervised fine-tuning on human demonstrations, robot trajectories, and simulated experience. The model averages 72.5 across 28 embodied benchmarks, setting a new open-source state of the art and performing on par with proprietary GPT-6-Astra and Gemini 3.6 Flash, with best open-source results on 14 benchmarks.

Hugging Face daily papers · 2d agoAI research1

Safe Meta-Reinforcement Learning via Information Space Reachability

Safe meta-RL framework reasons about safety in information space, learning a safety value function used for safety filtering and constrained policy optimization.

The paper proposes safe meta-RL that reasons about safety in information space, capturing both physical state and the agent's belief over the underlying task. A safety value function measures the probability of avoiding unsafe regions indefinitely and satisfies a self-consistency condition and Bellman equation, making it learnable via meta-RL. The resulting algorithm uses the learned function for safety filtering and constrained policy optimization, with effectiveness demonstrated on meta-RL benchmarks.

arXiv cs.AI / cs.LG / cs.CL · 2d agoAI research

ENCP: Episode-Normalized Conformal Prediction for Vision-and-Language Navigation

ENCP calibrates conformal prediction per navigation episode, giving step-level coverage guarantees for vision-language navigation agents despite within-episode dependence.

Episode-Normalized Conformal Prediction (ENCP) rescales a nonconformity score by a VLN policy's residual confidence and calibrates one maximum score per episode, preserving step-level coverage of at least 1−α despite dependence among steps within an episode. Across four VLN policies and three nonconformity scores on R2R and REVERIE, ENCP meets all reported empirical step-coverage targets in seen-to-unseen evaluation. The model-agnostic uncertainty estimates can signal when an agent should defer to a stronger predictor or human assistance.

arXiv cs.AI / cs.LG / cs.CL · 1d agoAI research

The Evolution of the Agent Harness

Latent Space essay argues late-2025 agent gains came from models and harnesses maturing together, with harness logic absorbed into model weights.

The piece defines the agent harness as everything beyond model weights—tools, context, memory, guardrails—and charts its evolution from ReAct prompting (October 2022) through AutoGPT's premature autonomy, Cursor/Copilot's human-in-the-loop retreat, and Devin's roughly 15% success rate, to o1's capability overhang and Claude Code's February 2025 terminal agent with permission rules. It argues the Christmas 2025 jump cited by Transformer co-inventor Lukasz Kaiser reflected model and harness curves crossing, and that remaining harnesses will serve human attention rather than the model.

Latent Space · 25d agoAI tools & infra

EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness?

Researchers introduce EVOHARNESSBENCH, a benchmark showing that evolving agent harnesses (tools, skills, agents) cause forgetting and inconsistent adaptation across 802 tasks.

The paper introduces EVOHARNESSBENCH, a benchmark that places non-stationarity in the externally supplied agent harness rather than in the task stream, evaluating agents across tools, skills, and specialist agents. It comprises 17 multi-stage harness streams built deterministically from verifier-based benchmarks, totaling 802 tasks, 520 tools, 42 skills, and 62 agents. Evaluation covers deployment (retention of previously accessible competence) and self-evolving adaptation settings. Results show harness expansion alone degrades previously solved tasks (harness-induced forgetting), adaptation gains are inconsistent, and retention and adaptation can pull in opposite directions.

Hugging Face daily papers · 13d agoAI research

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

Researchers propose ModularRSI, a modular benchmark-disjoint recursive self-improvement framework that evolves agent harnesses across five modules, improving TB2.0 and SWE-Bench Verified results.

ModularRSI targets generalizable recursive self-improvement (RSI) for agent harnesses by contrasting successful and failed trajectories for the same task and aggregating evidence across tasks to find recurring behavioral deficiencies. It decomposes the evolvable harness into five modules—Agent Loop, Tool Use, Observation Management, Context Management, and Task Completion Detection—each evolved independently within a restricted scope, then integrated with conflict resolution. Using 2,000 executable evolution tasks disjoint from evaluation benchmarks, it shows consistent gains on TB2.0 and SWE-Bench Verified and transfers across different foundation models.

Hugging Face daily papers · 2d agoAI research

EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents

EvoSafeHarness auto-synthesizes per-model, per-domain safety harnesses, cutting prompt-injection attack success on AgentDojo to 0.0% at 82.8% utility.

EvoSafeHarness is an optimization framework that synthesizes deployable safety harnesses for frozen LLM agents in a target domain, jointly searching natural-language policies and executable code logic guided by model behavior, domain specifications, and adversarial review. On DecodingTrust-Agent it reduces average attack success rate from 45.6% to 10.0% at a 3.3-point utility cost, and on AgentDojo reaches 82.8% utility at 0.0% ASR, twice CaMeL's utility at that operating point. It keeps mean ASR below 20% under adaptive PAIR attacks and transfers unchanged to unseen AgentDyn suites. The analysis finds domain semantics determine required safety relations while model and runtime behavior determine enforcement points.

Hugging Face daily papers · 11d agoAI safety & security

Embodied-BenchForge: A Closed-Loop Agentic Workflow for Embodied Benchmark Construction

Embodied-BenchForge automates embodied benchmark construction via closed-loop synthesis with verification and repair, yielding seven benchmarks for MLLM evaluation.

Embodied-BenchForge is an agentic framework that transforms user-specified evaluation intents into complete embodied benchmark artifacts via Closed-Loop Benchmark Synthesis. Skill-Orchestrated Artifact Synthesis composes typed reusable skills while an artifact dependency graph records intermediate outputs; Requirement-Guided Verification and Repair triggers local re-execution or upstream rollback on failures. It constructs six Offline EQA benchmarks plus one interactive benchmark with 220 executable tasks, distinguishing MLLM and embodied agent capabilities in observation-based understanding and closed-loop execution.

arXiv cs.AI / cs.LG / cs.CL · 5d agoAI research

Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision

ECCV 2026 challenge winner reformulates egocentric intervention timing as single-token classification, boosting macro-F1 by 0.249 over free-form generation.

The paper describes the winning submission to the EgoProactive track of the ECCV 2026 Wearable AI Challenge, ranking first in the large-model division and second in the <=2B division. The method reformulates intervention timing as single-token yes/no classification, improving macro-F1 by 0.249 and G-mean by 0.30 over free-form generation. Supervision generated by a tool-calling video agent transferred better than a narration-only dataset that was four times larger and ten times cheaper, suggesting visual grounding matters more than annotation volume.

Hugging Face daily papers · 6d agoAI research

Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning

Researchers analyze why Preventative Steering protects LLMs against malicious fine-tuning, finding active adaptation drives protection, and propose Progressive Intensity Scheduling.

The paper studies Preventative Steering, a training-time defense that injects undesirable-trait persona vectors during adversarial fine-tuning and removes them at evaluation time. Temporal analysis shows protection emerges from an early compensatory adaptation phase followed by a steady-state phase, with attention output projections acting as the dominant residual-write route for defensive updates. Intervention Delta Preservation experiments show that preserving or reinjecting weight offsets fails to maintain protection, indicating reliance on active adaptation rather than a static defense. The proposed Progressive Intensity Scheduling improves safety robustness on Qwen2.5 and Gemma-3 while reducing harmful trait expression.

arXiv cs.CR · 7d agoAI safety & security1

From Parameters to Answers: How LLMs Retrieve and Use Their Internal Knowledge

Interpretability study traces how Qwen, Llama, and Gemma route query information and internal knowledge across layers when answering questions.

Researchers used layerwise interventions on hidden states to separate query-routing signals from target knowledge in language models, testing Qwen, Llama, and Gemma on country-continent questions with varied answer types. A pair-conditioned request direction strengthens before interventions alter downstream knowledge, opening a causal window while answer-supporting content is still forming. Trajectories differ by model: Gemma shows a partially overlapping mid-layer routing profile, while Llama has no sustained routing-effect window under the same gates.

arXiv cs.AI / cs.LG / cs.CL · 6d agoAI research1

Does Your Agent's Memory Survive a Model Upgrade? A Controlled Study of Memory Portability

A controlled study finds agent memory portability varies sharply: fixed-schema knowledge graphs survive model swaps while compressed notes degrade.

The study compares preserving an agent's history as raw long context, RAG chunks, compressed natural-language notes, or fixed-schema knowledge graphs across model upgrades, using 48 synthetic histories and two open-weight sub-10B-parameter models. Fixed-schema KG accuracy changed by only +0.0004 ± 0.0020 after a writer swap, while compressed NOTES shifted asymmetrically by +9.91 or -13.28 percentage points depending on migration direction. Mixed 50/50 embedding migrations captured only 4.96 of an 11.90-point RAG re-embedding gain; 80% of the NOTES deficit came from information lost at construction, and 81% of the RAG deficit from retrieval failures. Store-only repair of NOTES failed to reach 90% recovery in all 48 cases, while retaining raw histories enabled recovery in 34 of 48 for one direction.

arXiv cs.AI / cs.LG / cs.CL · 12d agoAI research1

Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions

A linear hidden-state direction encodes question impossibility in 1.7B-70B LLMs, but misalignment with the safety-refusal pathway explains why models answer unanswerable questions.

The study examines why instruction-tuned LLMs from 1.7B to 70B parameters answer structurally unanswerable math and code questions instead of abstaining. A single linear direction in the hidden state separates answerable from impossible prompts, showing models represent impossibility before generation, but this direction is nearly orthogonal to the canonical safety-refusal direction. Generation-time steering along the recognition direction changes invalidity-aware behavior dose-responsively, and the geometry is present even at the pretraining endpoint, indicating a routing failure rather than an encoding failure.

Hugging Face daily papers · 18d agoAI safety & security

PlannerForge: LLM Agents for Scenario-Based Testing of Motion Planners in Autonomous Driving

PlannerForge unifies scenario-based testing of autonomous driving motion planners in one LLM-agent framework, outperforming prior baselines.

PlannerForge is an LLM-agent framework that covers the full scenario-based testing pipeline for autonomous driving systems, spanning scenario generation, selection, modification, routing, planner testing, plus new enhancement and benchmarking stages. In evaluations with 10 off-the-shelf LLMs, best-per-task scores range from 0.88 to 1.00, and open-source 20-35B backends such as Qwen3.6:35B match commercial APIs on most tasks. End-to-end chaining retains 83% (commercial) and 78% (open) of seed queries, beats Scenario Factory 2.0 on executable generation, and cost-tuning lifts planner success from 50.4% to 70.2% while cutting collisions from 19.0% to 8.4%.

Hugging Face daily papers · 8d agoAI research

ReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embodied Multimodal LLMs

ReactHuman benchmark tests whether multimodal LLMs react safely to sudden household hazards; seven evaluated models mishandle roughly one hazard in three.

ReactHuman is the first physics-grounded benchmark for human-like reactive decision-making, placing a multimodal LLM as the brain of a simulated humanoid facing 17 event families of sudden household hazards across over 1,000 bit-for-bit reproducible scenes with annotation-free ground truth from 240 Hz rigid-body simulation, including adversarial objects whose appearance contradicts their physics. A five-metric suite scores each reaction along reasonable, safe, and physically grounded axes, and every committed plan is physically executed. Seven representative MLLMs mishandle roughly one hazard in three, act from fixed dispositions rather than the observed scene, trust appearance over motion, and miss interception points at meter scale; none of these failures shrink with model scale.

Hugging Face daily papers · 7d agoAI research

Perturbation Probing: A New Diagnostic for the Fragility of LLM Safety

Unit 42 research shows LLM safety refusals concentrate in a thin neural layer, motivating external, multi-layered AI security controls.

Palo Alto Networks Unit 42 introduces Perturbation Probing, a diagnostic technique for measuring the fragility of LLM safety mechanisms. The research finds that safety refusal behavior is localized within a thin neural layer, implying small perturbations can undermine built-in refusals. The authors argue this motivates external, multi-layered security defenses on top of model-internal safety training.

Palo Alto Unit 42 · 18d agoAI safety & security

Qwen-Drive 1.0 tells you why it brakes, just don't expect the explanation to match the maneuver

Alibaba's Qwen-Drive 1.0 adds 3D perception and planning modules to Qwen3.5-4B for driving tasks, though explanations often mismatch maneuvers.

Qwen-Drive 1.0, built on Qwen3.5-4B, combines spatial perception, traffic question answering, and route planning in one vision-language model, adding a bird's-eye-view perception module and a Planning Expert trained via staged fine-tuning and reinforcement learning. The paper finds text-image models do not inherently grasp 3D space; spatial accuracy only improved when the base vision-language model itself was trained on spatial tasks, while avoiding catastrophic forgetting of general knowledge. The cut reinforcement learning-trained version halved road-departure rate in simulation from 24% to 12%, and the model beats specialized driving models in most of Qwen's benchmarks, but its explanations sometimes conflate causes like distant red lights and crossing children, and results partly rest on self-designed tests. The work follows prior findings from PaLM-E and a UC Santa Cruz adversarial sign attack on DriveLM showing VLM driving models' reasoning and spatial gaps.

The Decoder · 9d agoAI research