AI News Archive: August 4, 2026 — Part 14
Sourced from 500+ daily AI sources, scored by relevance.
- Balancing Efficiency and Efficacy: Training-Free Attention-Guided Switching Between Explicit and Latent Thoughts for MLLMs
Reasoning in Multimodal Large Language Models (MLLMs) requires both fine-grained visual perception and rigorous logical deduction. Explicit text-based Chain-of-Thought (CoT) is computationally expensive and prone to visual hallucinations, while existing latent reasoning methods typically require cos...
- Predicting Multilingual Classification and Translation Performance of LLMs with Cross-Lingual Alignment $\unicode{x2013}$ Is English Enough?
Multilingual large language models (LLMs) have been shown to perform better on non-English classification tasks when the representations of the given language are more aligned to English within the model. Several cross-lingual alignment (CLA) scores have been proposed for use with LLMs, along with m...
- Dynamically Allocating Evaluation Effort for Model Ranking
While human evaluation is the gold standard in many NLP tasks, it suffers from prohibitive costs and poor scalability. When identifying top-performing models, typical evaluation protocols waste effort by exhaustively evaluating all models on the entire benchmark, a safe but inefficient approach. In ...
- DUD: Decoupled Update Dynamics for Reliable Uncertainty Quantification in Large Language Models
Accurate Uncertainty Quantification (UQ) is critical for reliable deployment of Large Language Models (LLMs), yet traditional probability-based metrics often fail to capture the model's true epistemic state. While recent mechanistic approaches leverage hidden state dynamics, they typically aggregate...
- Don't Let Me Ask for It: LLMs Show Deficiencies in Active Multi-Turn Information Acquisition for Abductive Inference
Abductive reasoning requires forming hypotheses that explain observed evidence and revising them as new evidence becomes available. While large language models (LLMs) are often evaluated on whether they solve abductive reasoning tasks correctly, less is known about how they acquire evidence, update ...
- ArtECulture: Benchmarking Culture-Conditioned Visual Emotion Understanding in Multimodal Large Language Models
Existing visual emotion understanding methods typically ignore cultural variations in emotional perception. We introduce culture-conditioned visual emotion understanding, a task that predicts the culture-specific emotional perception of a given image and explains the underlying rationale. Although r...
- Benchmarking the Benchmarks: Testing the Predictive Validity of Commonsense Benchmarks
Predicting LLM's capabilities on real-world tasks is essential, yet the extent to which performance on commonsense benchmarks predicts downstream performance remains underspecified. To establish the practical usability of widely adopted commonsense benchmarks, we evaluate 23 models from six families...
- Distractor-Aware Truncation: Disentangling Context-Length Effects from Signal Loss in Long-Context LLM Benchmarks
A standard claim in the literature on retrieval-augmented and memory-augmented language models is that shorter context is better when the relevant information is preserved. We test this claim by running every sample of two long-context benchmarks -- BABILong and GraphWalks (BFS) -- at four context-r...
- The Tell-Tale Trace: Detecting Reasoning Failures in LLMs Using Chain-of-Thought Dynamics
Chain-of-thought (CoT) reasoning improves large language model (LLM) performance while also providing an observable interface to the model's reasoning process. Existing approaches that leverage verbalized CoTs to monitor reasoning correctness, however, largely evaluate the semantic correctness or co...
- MoEGen: Mixture-of-Experts for Instance-Adaptive LoRA Generation
Parameter-efficient fine-tuning (PEFT) enables efficient adaptation of large language models, but existing MoE-based PEFT methods typically improve capacity by storing multiple full LoRA experts, causing adapter storage to grow linearly with the number of experts and restricting adaptation to a fixe...
- CIGTSurv: Clinical Information Guided Tri-modal Survival Prediction with Local Prototype Association and Global Feature Alignment
Multimodal learning has significantly advanced survival prediction by integrating pathology images with genomic data. However, clinical information, despite its critical role in reflecting a patient' s overall health, remains underutilized due to its discrete, sparse, and low-dimensional nature. Fur...
- Relational Priors as Convergence Pressure in LLM-Based Multi-Agent Systems
Large language model-based multi-agent systems (LLM-MAS) are designed through roles, debate protocols, and aggregation rules. These choices create implicit social expectations: agents may be expected to trust, challenge, defer to, or collaborate with peers. We study the effects of making inter-agent...
- On the Diversity of Analogy Making in Large Language Models
Large Language Models (LLMs) have demonstrated remarkable potential for analogy making, a core cognitive capability that drives novelty and creativity. While prior research has extensively investigated the applications and underlying mechanisms of LLM-based analogy making, its output diversity remai...
- Agentic Reinforcement Learning with Self-Distilled Reward Shaping
Agentic reinforcement learning enables LLM agents to learn through interaction, but sparse trajectory-level rewards reveal success without identifying which intermediate decisions deserve credit. Training-only privileged skills can provide denser supervision by allowing the same frozen policy snapsh...
- Reachability Is Not Realization: Tracing the Sources of LLM Benchmark Gains
Benchmark gains are often treated as evidence of greater LLM capability. Yet the same gain can reflect different changes in model behavior. A model may reach new answers, or produce answers that were already within reach. Aggregate scores do not distinguish these changes question by question. We est...
- GROW: Group-Relative Advantage-Weighted On-Policy Reinforcement Learning of Autoregressive-Diffusion Text-to-Speech model
Reinforcement learning for flow-matching text-to-speech is complicated by deterministic ODE sampling: trajectory-level policy-gradient methods typically convert the ODE into an SDE and track per-step likelihood ratios, introducing stochastic perturbations and substantial overhead. We propose GROW, a...
- EduClaw-Bench: A Long-Horizon Benchmark for Pedagogical LLM Agents with Simulated Learners
Large language models (LLMs) power educational applications from tutoring to essay scoring, but each is a point solution to a single task, and only recently have these point solutions been integrated into agents operating over a learning management system (LMS). Yet tutoring is long-horizon, since a...
- Aligning Large Vision-Language Models at Test Time: A Trajectory-Guided Structured Sampling Approach
Post-training reinforcement learning (RL) algorithms are commonly used to align large vision-language models (LVLMs) with human intent and the requirements of visual reasoning tasks. However, existing RL-based alignment methods are often resource-intensive and encounter mismatches between training o...
- Evidence-Grounded Multimodal Knowledge Graph Construction for Multi-Lecture Educational Reasoning
Lecture videos distribute knowledge across speech, slide text, diagrams, equations, and presentation order, which transcript-only retrieval does not fully preserve. This paper presents an evidence-grounded multimodal pipeline that transcribes lectures, selects semantic anchors, applies optical chara...
- An Actionable Diagnosis of Multilingual, Multi-Agent Planning Failures
Multilingual multi-agent systems exhibit substantial degradation beyond English, yet prior work rarely identifies how task-critical information is lost when user requests are converted into executable plans. We study the planner in a multi-agent system as the request-to-action interface and derive a...
- When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills
Persona skills distill personal interaction histories into portable and executable artifacts for downstream agents. While enabling flexible personalization, this process concentrates fragmented personal signals, amplifies their impact through reuse, and challenges defenses designed for individual re...
- Finyuus
A code-first language for durable, governed AI workflows
- VetScore: Risk-Weighted Fact Verification for Veterinary Long-Form QA with Citations
Citation excerpts can be used to increase the reliability of generated outputs and their faithfulness to cited sources, which is especially important in high-stakes domains such as human and veterinary medicine. However, this does not guarantee that generated claims are faithful to the provided exce...
- LoopMTP: A looped transformer guided by latent multi-token prediction
Looped transformers have emerged as a parameter-efficient alternative to scaling depth for strong reasoning. By reusing one stack of layers across $T$ iterations, they attain the effective depth and reasoning capabilities of larger models at a fixed parameter count. Yet existing approaches suffer fr...
- Disentangling Language Modeling and Boundaries
Byte-level language models are usually argued for on the grounds of robustness, multilingual fairness, and character-level skills. We point to a different, structural advantage: because they read and write bytes, any two of them share an output space, so knowledge transfer between them is exact and ...
- Looking under the Wrong Lamppost: On the Limitations of Automated Translation Quality Estimation
Automation of Translation Quality Estimation (QE) has emerged as a widely discussed approach to managing translation quality at scale, and a growing number of tools and technologies have been released in pursuit of this goal. However, the proliferation of new QE systems has not always been accompani...
- Consensus Measures for Unstructured Biomedical Text Annotations
Biomedical literature is increasingly mined for knowledge beyond the questions it was written to answer. Because the target concepts are not known in advance, annotators prefer open-ended labels, whose agreement is hard to quantify. We study soft inter-rater reliability for annotators providing unst...
- ChronoLens: Measuring Language Change Across Time, Languages, and Linguistic Levels
Historical language change affects morphology, syntax, semantics, and pragmatics, yet computational studies typically examine these levels with incompatible representations and therefore cannot determine whether they evolve together across languages. We address this problem by asking how the magnitu...
- Efficient Multilingual Neural Machine Translation via Corpus-Driven Vocabulary Pruning: An English-Arabic Case Study
The adoption of large pre-trained multilingual models for neural machine translation (MNMT) faces a major challenge: excessive memory and computational consumption due to overly large vocabularies and embedding layers. Although existing compression methods like pruning, quantization and knowledge di...
- Probing Character-level Transformers for the Spanish L-shaped Morphome
When a transformer learns an irregular morphological pattern, what has it learned? Our test case is the Spanish \emph{L-shaped morphome}, a complex irregular pattern in which the verb's stem alternates in exactly the first-person singular indicative and all subjunctive forms, and whose membership no...
- FACTWASH: Catching AI Rewrites That Wash Hearsay into Fact
AI systems rewrite information constantly: conversations become stored memories, documents become answers. The rewrite can keep a claim while washing away what made it checkable, who said it, how sure they were, when it held. We call that failure factwashing, and release factwash, an open-source wri...
- ICO: Enhancing Semantic-Shift Jailbreaks via Iterative Context Optimization
Foundation models have achieved remarkable success across diverse tasks, but they remain vulnerable. To investigate such vulnerabilities, semantic-shift jailbreaks have recently emerged as a promising attack paradigm. They bypass explicit safety mechanisms by replacing harmful terms in original harm...
- Hey Noah
A proactive AI executive assistant for founders
- Wondering
Duolingo for learning anything
- Atlaso
One memory for every AI you use
- Dashi Metrics
Visualize your revenue on a 3D globe
- Driven
The trusted AI investment agent, from insight to action
- Vibe Buddy
Hardware for AI coding
- Screen Awesome
The free screen recorder that cannot upload your video
- ZapDigits MCP
The MCP server for marketing data
- VIDEO AI ME
Make videos and post them everywhere with just one tool
- GrowthBook 5.0
Build, ship, and improve at scale
- Domo
Build and customize your own calendar agent you can text
- MOTHER
A terminal built for Claude Code w/ one-click session resume
- ScrollToll
Counts every Reel you watch, then locks the app.
- Karve
The API client for developers on Windows
- Tixio 3.0
Start meetings from chat
- AirProof AI
Find the best spot for your air purifier in seconds
- Stynar
The AI SDR that runs outbound for you
- Crodo AI
Your voice-first AI assistant for macOS