New Model Releases A

CORA analyzes the gap between a model's reasoning and its final answer when extending verifiable-reward RL to multimodal settings. It proposes consistency-oriented reasoning alignment to bridge that gap.

The paper studies active learning for multi-group mean estimation framed as a d-armed bandit minimizing max-risk. It introduces a complexity measure characterizing the difficulty of adaptive budget allocation.

The work casts online inventory optimization as online convex optimization with memory, where carryover makes the feasible set history-dependent. It develops an optimal hidden-target learning method on general convex sets.

AgentSpec studies scaffolded LLM agents that combine reasoning, memory, reflection, and action through controlled composition. It aims to isolate how each component contributes to overall performance.

LLMs serve as execution engines for agentic systems yet still consume context through a sequential text interface, mismatching modern structured workflows with independent parallel branches. The paper explores synthesizing such parallel branches directly in latent space.

This work targets knowledge editing that updates selected facts while preserving nearby behavior in a memory-assisted setting. It proposes route-specialized dual adapters that decide when to write and when to suppress edits.

As AI automates real-world computer vision applications such as autonomous vehicle control, this paper demonstrates acoustic adversarial attacks that can disrupt CV systems, highlighting a new physical, sound-based attack surface.

Time-stamped interaction logs objectively record digital app usage, but their granularity and noise obscure meaningful insights into work. The paper proposes abstracting cross-domain action sequences into interpretable workflows.

The paper studies online convex optimization over a convex set where the learner may use only a sublinear number of noisy probes. It provides theoretical guarantees under this limited-probe setting.

Survival prediction is central for healthcare providers and clinical researchers. The paper introduces expert-driven survival machines that improve risk stratification and interpretability across multiple clinical cohorts.

Online group chats have rarely-stated local conversational norms. LoSoNA is a benchmark measuring whether LLM-based agents can recognize and adapt to these local social norms.

Clustering is widely used but its outputs are hard to interpret and audit. Cluster LOCO provides feature-importance scores to explain what distinguishes each cluster.

Generative dynamics models enable planning in challenging robotic systems, but safe deployment requires reliably detecting policy-induced out-of-distribution transitions. The paper proposes sensitivity shaping for latent modeling to improve such OOD detection.

Route optimization is vital for safety and punctuality in railway operations, especially in heterogeneous multi-gauge networks. The paper proposes a temporal planning framework for disruption-aware dynamic route optimization.

Giving LLMs direct control over costly, irreversible experiments invites unsafe exploration, while discarding their creativity sacrifices optimization. CARE controls LLM-generated policies through auditable review of evidence in scientific experimentation.

LLMs are increasingly deployed as planners for autonomous agents in household environments. Whereas existing benchmarks only check whether generated plans execute, SIMMER uses a world model to benchmark their latent failures.

A core role of personal-agent memory is turning stored information and prior interactions into future-oriented assistance. StreamMemBench provides a streaming evaluation of agent memory using cues from what the agent observes and how users interact.

Emulators cheaply reproduce regional climate models' downscaling, linking global-model predictors to high-resolution fields. The paper assesses the added value of diffusion-based generative machine learning for regional climate model emulation.

Two-finger grippers dominate manipulation research but are limited by their form factor. ORCA is an open-source platform to support research on more dexterous robotic manipulation.

Autonomous robots may need decisions based on evidence no longer visible. For delayed-evidence tasks, where an early cue disappears before a later decision, TRACE introduces trajectory-routed causal memory for visuomotor imitation.

PCA preserves variance, not the information needed to detect rare catastrophic events. The paper proves a risk shadow where even very high variance preservation can cause catastrophic decision errors.

BayLing-Duplex enables native full-duplex speech interaction with a single autoregressive LLM, letting it listen and speak simultaneously. It handles natural phenomena such as overlap and hesitation.

LLM-based guardrails effectively defend autonomous agents against prompt injection and jailbreaks. The paper reveals that the very reasoning and instruction-following abilities enabling this defense can be turned into denial-of-service attacks against the guardrails.

AI evaluations are widely used to track progress, but inconsistencies across evaluators hinder analysis and comparison. The paper proposes a unifying schema and a community repository, Every Eval Ever, for AI evaluation results.

Macrocyclic peptides are promising for intracellular targets but require joint control of non-natural chemistry, ring topology, and permeability. PepALD generates them using autoregressive latent diffusion.

LLM reasoning is ephemeral: chains of thought vanish, pruned branches leave no record, and memory cannot be diffed or merged. GitOfThoughts makes reasoning and agent memory version-controlled, so it can be replayed, diffed, and merged.

The paper investigates the fragility of post-hoc explanations in audio deepfake detection. Introducing a psychoacoustic framework beyond image-style Lp metrics, it shows attributions can be manipulated while predictions remain unchanged.