Liquid AI Releases LFM2.5-DSpark Draft Models That Deliver Up to 3.18x Faster Decoding Without Changing Model Outputs
Three ~300M drafters bring speculative decoding to LFM2.5, delivering up to 3.18x faster decoding with identical greedy output.
The post Liquid AI Releases LFM2.5-DSpark Draft Models That Deliver Up to 3.18x Faster Decoding Without Changing Model Outputs appeared first on MarkTechPost.
Ramp launches its own AI model router, called Router
Ramp has launched its own AI model routing service, dubbed Router, that lets users and companies use and switch between various large language models via an API.
What a production incident taught me about trusting a model to judge another model's work
The post The LLM Judge That Kept Agreeing With Itself appeared first on Towards Data Science.
Meta brings Pocket, an app that lets you vibe-code and share games, to US users
Meta is bringing Pocket, its experimental AI-powered app for creating and sharing interactive games, to users across the U.S. after quietly testing it in Brazil.
“Runaway” AI, “rogue” agents, and “autonomous” actors—the current rhetoric would have you believe that AI agents are not only awake and aware, but angry at their creators. Prominent tech leaders such as Demis Hassabis, Dario Amodei, and Sam Altman push for regulation of these seemingly “superhuman” ...
Three Kinds of RAG Corpus, and What It Costs to Build for the Wrong One
Enterprise Document Intelligence [Vol.1 #14A] - Three questions tell you which shape a document collection has, and each shape wants a different architecture
The post Three Kinds of RAG Corpus, and What It Costs to Build for the Wrong One appeared first on Towards Data Science.
Making the Knowledge Layer a Graph You Actually Traverse
Why retrieval quality should be a property of the system, not of the question's wording? Rebuilding knowledge layer with graph traversal on every query, bitemporal edges, and two-threshold entity resolution.
The post Making the Knowledge Layer a Graph You Actually Traverse appeared first on Towards ...
In 2026, the software engineering community is divided by a simple question: Should AI engineers still read the code generated by their agents? One camp argues that code has become virtually free to produce and discard, so humans should focus on systems and guardrails rather than implementation deta...
Unlocking hidden revenue streams with market models
Each day, an airline transports tens of thousands of passengers on hundreds of flights. Often these are not straightforward point-to-point routes, with passengers requiring multiple connections. The airline can consider potentially hundreds of variables to price each of these journeys: demand, seaso...
Auditing Preference Biases and Fine-Tuning Language Models with Direct Preference Optimization on Anthropic HH-RLHF Using TRL and LoRA
This tutorial provides an end-to-end workflow for fine-tuning language models using Direct Preference Optimization (DPO). We demonstrate how to audit the Anthropic HH-RLHF dataset for structural and length-based biases, implement a robust training pipeline using TRL and LoRA, and evaluate model perf...
Position: Collusion Risks Among AI Reasoning Agents Justify Certification Requirements for Making Market Decisions
arXiv:2608.18078v1 Announce Type: new
Abstract: This position paper argues that AI agents with chain-of-thought reasoning capabilities are predisposed to exhibit collusive behavior and should be required to obtain behavioral certification before making decisions that affect economic markets. This i...
Position: Profiling Game Worlds by Transition Complexity
arXiv:2608.18079v1 Announce Type: new
Abstract: Game world modeling (GWM) and reinforcement learning (RL) are often confounded because research papers rarely quantify how difficult the underlying transition prediction problem is at the declared interface (pixels/tokens/latents with finite history)....
Position: Behavioral Systems Require Behavioral Tests
arXiv:2608.18081v1 Announce Type: new
Abstract: Artificial agentic systems increasingly operate as behavioral systems by interacting with dynamic environments, pursuing goals, and adapting over time. Yet, current evaluation methods largely focus on performance outcomes, not the underlying behaviora...
Position: Current Model Cards Are Insufficient for Downstream Governance of Open-Weight Foundation Models
arXiv:2608.18086v1 Announce Type: new
Abstract: The growth of open-weight foundation models (OWFMs) has prompted the AI community to re-evaluate strategies for effective downstream governance. Although model cards have been widely adopted as transparency artifacts in model repositories, existing fr...
arXiv:2608.18147v1 Announce Type: new
Abstract: Adaptive stochastic quantization (ASQ) is a recently introduced quantization approach that optimizes the Mean Squared Error (MSE) for a given input while preserving unbiasedness. It is designed to alleviate the communication and memory bottlenecks of ...
Towards Reversible Forgetting: Managing Obsolete Knowledge in Continual Enterprise AI Agents
arXiv:2608.18177v1 Announce Type: new
Abstract: Continual learning has traditionally treated forgetting as a failure, emphasizing preservation of previously acquired knowledge as environments evolve. We argue that this objective is incomplete for enterprise AI agents operating in non-stationary env...
Accelerating Visual On-Policy Distillation with Batched Speculative Jacobi Rollouts
arXiv:2608.18183v1 Announce Type: new
Abstract: Visual on-policy distillation (OPD) improves the training of compact visual autoregressive models by learning from trajectories generated by the current student. However, these online rollouts are still produced token by token with autoregressive deco...
H$^2$EDL: Hyper Evidential Deep Learning for Hierarchical Classification
arXiv:2608.18185v1 Announce Type: new
Abstract: Fine-grained recognition often involves hierarchical label spaces, where a model may be confident about a coarse semantic concept while remaining uncertain among its descendant classes. Such structured ambiguity requires uncertainty representations th...
Multilingual Knowledge Transfer under Data Constraints via Lexical Interventions
Cross-lingual knowledge transfer is critical for building high-performing multilingual language models for languages with insufficient training data. When target language data is scarce, the knowledge required for many downstream tasks involving scientific reasoning, commonsense inference, and world...
Scaling Laws for Mixture Pretraining Under Data Constraints
As language models scale, the amount of data they require grows – yet many target data sources, such as low-resource languages or specialized domains, are inherently limited in size. A common strategy is to mix this scarce but valuable target data with abundant generic data, which presents a fundame...