A new causal method named RAW (Refusal Aversion in the Wild) uses LLM stochasticity to measure how often user refusals lead to platform abandonment. By analyzing existing interaction logs, you can identify the exact causal effect of refusals on subsequent user re-engagement.
Researchers introduced ActGCG, a method to replicate the effects of activation steering—typically requiring internal model access—by optimizing input suffixes. The technique successfully reproduces specific behaviors like language steering through external text inputs alone.
Researchers have established the theoretical maximum reward gain possible during language model alignment under fixed KL-divergence constraints. The findings demonstrate that 'best-of-N' sampling effectively reaches these theoretical bounds, whereas common reinforcement learning approaches like PPO and GRPO currently fall short of optimal performance.
A new method called FlagRot optimizes key-value (KV) cache quantization for long-context models. By selectively rotating key segments based on attention error rather than applying global rotation, it reduces accuracy loss in 2-bit or 4-bit caches.
New research shows that reasoning history can be rewritten into compact state records before new tool results are introduced. This method effectively reduces future reasoning tokens and total agent spending by eliminating redundant thoughts without requiring model retraining.
Apple researchers have unveiled an online training infrastructure for mobile UI agents that utilizes a two-part architecture to split navigational logic from visual interpretation. By employing step-level feedback provided by an LLM-as-a-Judge and a novel value estimation technique known as GiGPPO, these agents demonstrate significantly better adaptability than static models trained on pre-recorded sequences.
Recent research shows that many attention heads in large language models are redundant and specifically contribute to verbatim memorisation of training data. By selectively pruning these heads at inference time, researchers achieved a 91.5% reduction in memorisation events while simultaneously improving performance on standard benchmarks.
Researchers have proposed 'Artifact Distillation,' a method where frontier models externalize their reasoning into an 'artifact bank.' Smaller models query this bank at inference time to improve performance without requiring expensive model retraining or gradient updates.
Researchers have developed TraceQuery, a sparse decoding framework that reduces the computational cost of diffusion large language models (dLLMs). By analyzing denoising trajectories, the method selectively recomputes only necessary token representations rather than performing redundant operations, maintaining high accuracy with fewer computations.
IBM Research released vLLM-Hook MIA, a plugin for the open-source vLLM inference engine that lets developers observe and intervene in a model's internal states at runtime — for example to decline malicious prompts, flag hallucinated facts, or adjust tone — without disabling vLLM's fast graph-replay execution mode. According to IBM's technical report, MIA is up to 20x faster than the earlier vLLM-Hook and up to 14x faster than methods that insert code directly into the model. In tests, steering an 8B Llama or 1.5B Qwen model added only about 2% latency, and a 70B Llama model added about 6%.
Google Research announced the final milestone of its Coral NPU open hardware standard — a 32-bit RISC-V architecture with a new Matrix Execution Unit for up to 1 TOPS at roughly 10mW — plus a v1.0 open-source IREE/MLIR compiler that takes JAX, PyTorch and TensorFlow models directly to the hardware. Synaptics is launching the first commercial silicon built on this standard, including the Astra SR200 microcontroller series (400 GOPS) and new Coralboard SR and SL developer kits, with the SL now generally available via DigiKey. Google is also partnering with VeriSilicon and GlobalFoundries to bring the open RTL into production chips.
AWS released a push-based NIXL connector for vLLM that changes how key-value (KV) cache data moves between prefill and decode instances in disaggregated LLM serving. Instead of the decode instance pulling KV blocks after prefill finishes, the decode instance registers its target memory in advance and the prefill instance writes the KV data directly once ready, moving coordination work off the critical path. Benchmarked on a 1-prefill/1-decode Qwen3-32B deployment using EC2 P5en instances with EFA, push mode delivered up to 3x better time-to-first-token (TTFT) and up to 30% better time-per-output-token (TPOT) than the default pull mode, especially under high request rates.
IBM Research used a coordinated multi-agent 'agent factory' to explore hardware design optimizations for a quantum error-correction decoder, comparing proprietary and open frontier models under the same 100-hypothesis search budget. The open-model configuration, run on-premises via IBM's llm-d distributed inference framework, achieved a 52x speedup over baseline for about $26 in inference cost, versus $299 for a proprietary-model configuration that reached a higher 204x speedup. The study highlights that cache-aware routing and efficient serving (98% prefix-cache hit rate, ~$0.11 per million tokens) made the open-model approach dramatically cheaper while still finding valid, compact hardware designs.
Amazon Web Services researchers published a method called 'priming' that converts pretrained Transformer models into hybrid architectures mixing attention and state space model (SSM) layers, reusing existing weights instead of retraining from scratch. The approach cuts pretraining costs by over 99% and lets a 32-billion-parameter hybrid model match its source Transformer's quality while decoding up to twice as fast. Amazon tested three SSM types and released an open-source model zoo, training code, and serving tools under Apache 2.0.